ba-thesis/latex/thesis/chapters/proximal_decoding.tex
2023-04-24 23:23:35 +02:00

2286 lines
101 KiB
TeX

\chapter{Proximal Decoding}%
\label{chapter:proximal_decoding}
In this chapter, the proximal decoding algorithm is examined.
First, the algorithm itself is described and some useful considerations
concerning the implementation are presented.
Simulation results are shown, based on which behavior of the
algorithm is investigated for different codes and parameters.
Finally, an improvement on proximal decoding is proposed.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Decoding Algorithm and Implementation}%
\label{sec:prox:Decoding Algorithm}
Proximal decoding was proposed by Wadayama et al. as a novel formulation of
optimization-based decoding \cite{proximal_paper}.
With this algorithm, minimization is performed using the proximal gradient
method.
In contrast to \ac{LP} decoding, which will be covered in chapter
\ref{chapter:lp_dec_using_admm}, the objective function is based on a
non-convex optimization formulation of the \ac{MAP} decoding problem.
In order to derive the objective function, the authors begin with the
\ac{MAP} decoding rule, expressed as a continuous maximization problem%
\footnote{The expansion of the domain to be continuous doesn't constitute a
material difference in the meaning of the rule.
The only change is that what previously were \acp{PMF} now have to be expressed
in terms of \acp{PDF}.}
over $\boldsymbol{x}$:%
%
\begin{align}
\hat{\boldsymbol{x}} = \argmax_{\tilde{\boldsymbol{x}} \in \mathbb{R}^{n}}
f_{\tilde{\boldsymbol{X}} \mid \boldsymbol{Y}}
\left( \tilde{\boldsymbol{x}} \mid \boldsymbol{y} \right)
= \argmax_{\tilde{\boldsymbol{x}} \in \mathbb{R}^{n}} f_{\boldsymbol{Y}
\mid \tilde{\boldsymbol{X}}}
\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right)
f_{\tilde{\boldsymbol{X}}}\left( \tilde{\boldsymbol{x}} \right)%
\label{eq:prox:vanilla_MAP}
.\end{align}%
%
The likelihood $f_{\boldsymbol{Y} \mid \tilde{\boldsymbol{X}}}
\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right) $ is a known function
determined by the channel model.
The prior \ac{PDF} $f_{\tilde{\boldsymbol{X}}}\left( \tilde{\boldsymbol{x}} \right)$ is also
known, as the equal probability assumption is made on
$\mathcal{C}$.
However, since the considered domain is continuous,
the prior \ac{PDF} cannot be ignored as a constant during the minimization
as is often done, and has a rather unwieldy representation:%
%
\begin{align}
f_{\tilde{\boldsymbol{X}}}\left( \tilde{\boldsymbol{x}} \right) =
\frac{1}{\left| \mathcal{C} \right| }
\sum_{\boldsymbol{c} \in \mathcal{C} }
\delta\big( \tilde{\boldsymbol{x}} - \left( -1 \right) ^{\boldsymbol{c}}\big)
\label{eq:prox:prior_pdf}
.\end{align}%
%
In order to rewrite the prior \ac{PDF}
$f_{\tilde{\boldsymbol{X}}}\left( \tilde{\boldsymbol{x}} \right)$,
the so-called \textit{code-constraint polynomial} is introduced as%
%
\begin{align*}
h\left( \tilde{\boldsymbol{x}} \right) =
\underbrace{\sum_{i=1}^{n} \left( \tilde{x_i}^2-1 \right) ^2}_{\text{Bipolar constraint}}
+ \underbrace{\sum_{j=1}^{m} \left[
\left( \prod_{i\in N_c \left( j \right) } \tilde{x_i} \right)
-1 \right] ^2}_{\text{Parity constraint}}%
.\end{align*}%
%
The intention of this function is to provide a way to penalize vectors far
from a codeword and favor those close to one.
In order to achieve this, the polynomial is composed of two parts: one term
representing the bipolar constraint, providing for a discrete solution of the
continuous optimization problem, and one term representing the parity
constraints, accommodating the role of the parity-check matrix $\boldsymbol{H}$.
The prior \ac{PDF} is then approximated using the code-constraint polynomial as:%
%
\begin{align}
f_{\tilde{\boldsymbol{X}}}\left( \tilde{\boldsymbol{x}} \right)
\approx \frac{1}{Z}\mathrm{e}^{-\gamma h\left( \tilde{\boldsymbol{x}} \right) }%
\label{eq:prox:prior_pdf_approx}
.\end{align}%
%
The authors justify this approximation by arguing that for
$\gamma \rightarrow \infty$, the approximation in equation
(\ref{eq:prox:prior_pdf_approx}) approaches the original function in equation
(\ref{eq:prox:prior_pdf}).
This approximation can then be plugged into equation (\ref{eq:prox:vanilla_MAP})
and the likelihood can be rewritten using the negative log-likelihood
$L \left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right) = -\ln\left(
f_{\boldsymbol{Y} \mid \tilde{\boldsymbol{X}}}\left(
\boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right) \right) $ as%
%
\begin{align*}
\hat{\boldsymbol{x}} &= \argmax_{\tilde{\boldsymbol{x}} \in \mathbb{R}^{n}}
\mathrm{e}^{- L\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right) }
\mathrm{e}^{-\gamma h\left( \tilde{\boldsymbol{x}} \right) } \\
&= \argmin_{\tilde{\boldsymbol{x}} \in \mathbb{R}^n}
L\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right)
+ \gamma h\left( \tilde{\boldsymbol{x}} \right)%
.\end{align*}%
%
Thus, with proximal decoding, the objective function
$g\left( \tilde{\boldsymbol{x}} \right)$ considered is%
%
\begin{align}
g\left( \tilde{\boldsymbol{x}} \right) = L\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}}
\right)
+ \gamma h\left( \tilde{\boldsymbol{x}} \right)%
\label{eq:prox:objective_function}
\end{align}%
%
and the decoding problem is reformulated to%
%
\begin{align*}
\text{minimize}\hspace{2mm} &L\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right)
+ \gamma h\left( \tilde{\boldsymbol{x}} \right)\\
\text{subject to}\hspace{2mm} &\tilde{\boldsymbol{x}} \in \mathbb{R}^n
.\end{align*}
%
For the solution of the approximate \ac{MAP} decoding problem using the
proximal gradient method, the two parts of equation
(\ref{eq:prox:objective_function}) are considered separately:
the minimization of the objective function occurs in an alternating
fashion, switching between the negative log-likelihood
$L\left( \boldsymbol{y} \mid \boldsymbol{x} \right) $ and the scaled
code-constraint polynomial $\gamma h\left( \boldsymbol{x} \right) $.
Two helper variables, $\boldsymbol{r}$ and $\boldsymbol{s}$, are introduced,
describing the result of each of the two steps.
The first step, minimizing the log-likelihood, is performed using gradient
descent:%
%
\begin{align}
\boldsymbol{r} \leftarrow \boldsymbol{s} - \omega \nabla
L\left( \boldsymbol{y} \mid \boldsymbol{s} \right),
\hspace{5mm}\omega > 0
\label{eq:prox:step_log_likelihood}
.\end{align}%
%
For the second step, minimizing the scaled code-constraint polynomial, the
\textit{proximal operator} of $\gamma h\left( \tilde{\boldsymbol{x}} \right) $
has to be computed.
It is then immediately approximated with gradient-descent:%
%
\begin{align*}
\textbf{prox}_{\gamma h} \left( \tilde{\boldsymbol{x}} \right) &\equiv
\argmin_{\boldsymbol{t} \in \mathbb{R}^n}
\gamma h\left( \boldsymbol{t} \right) +
\frac{1}{2} \left\Vert \boldsymbol{t} - \tilde{\boldsymbol{x}} \right\Vert \\
&\approx \tilde{\boldsymbol{x}} - \gamma \nabla h \left( \tilde{\boldsymbol{x}} \right),
\hspace{5mm} \gamma > 0, \text{ small}
.\end{align*}%
%
The second optimization step thus becomes%
%
\begin{align*}
\boldsymbol{s} \leftarrow \boldsymbol{r} - \gamma \nabla h\left( \boldsymbol{r} \right),
\hspace{5mm}\gamma > 0,\text{ small}
.\end{align*}
%
While the approximation of the prior \ac{PDF} made in equation (\ref{eq:prox:prior_pdf_approx})
theoretically becomes better
with larger $\gamma$, the constraint that $\gamma$ be small is important,
as it keeps the effect of $h\left( \tilde{\boldsymbol{x}} \right) $ on the landscape
of the objective function small.
Otherwise, unwanted stationary points, including local minima, are introduced.
The authors say that ``[\ldots] in practice, the value of $\gamma$ should be adjusted
according to the decoding performance'' \cite[Sec. 3.1]{proximal_paper}.
%The components of the gradient of the code-constraint polynomial can be computed as follows:%
%%
%\begin{align*}
% \frac{\partial}{\partial x_k} h\left( \boldsymbol{x} \right) =
% 4\left( x_k^2 - 1 \right) x_k + \frac{2}{x_k}
% \sum_{i\in \mathcal{B}\left( k \right) } \left(
% \left( \prod_{j\in\mathcal{A}\left( i \right)} x_j\right)^2
% - \prod_{j\in\mathcal{A}\left( i \right) }x_j \right)
%.\end{align*}%
%\todo{Only multiplication?}%
%\todo{$x_k$: $k$ or some other indexing variable?}%
%%
In the case of \ac{AWGN}, the likelihood
$f_{\boldsymbol{Y} \mid \tilde{\boldsymbol{X}}}
\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right)$
is%
%
\begin{align*}
f_{\boldsymbol{Y} \mid \tilde{\boldsymbol{X}}}
\left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right)
= \frac{1}{\sqrt{2\pi\sigma^2}}\mathrm{e}^{
-\frac{\lVert \boldsymbol{y}-\tilde{\boldsymbol{x}}
\rVert^2 }
{2\sigma^2}}
.\end{align*}
%
Thus, the gradient of the negative log-likelihood becomes%
\footnote{For the minimization, constants can be disregarded. For this reason,
it suffices to consider only proportionality instead of equality.}%
%
\begin{align*}
\nabla L \left( \boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right)
&\propto -\nabla \lVert \boldsymbol{y} - \tilde{\boldsymbol{x}} \rVert^2\\
&\propto \tilde{\boldsymbol{x}} - \boldsymbol{y}
,\end{align*}%
%
allowing equation (\ref{eq:prox:step_log_likelihood}) to be rewritten as%
%
\begin{align*}
\boldsymbol{r} \leftarrow \boldsymbol{s}
- \omega \left( \boldsymbol{s} - \boldsymbol{y} \right)
.\end{align*}
%
One thing to consider during the actual decoding process, is that the gradient
of the code-constraint polynomial can take on extremely large values.
To avoid numerical instability, an additional step is added, where all
components of the current estimate are clipped to $\left[-\eta, \eta \right]$,
where $\eta$ is a positive constant slightly larger than one:%
%
\begin{align*}
\boldsymbol{s} \leftarrow \Pi_{\eta} \left( \boldsymbol{r}
- \gamma \nabla h\left( \boldsymbol{r} \right) \right)
,\end{align*}
%
$\Pi_{\eta}\left( \cdot \right) $ expressing the projection onto
$\left[ -\eta, \eta \right]^n$.
The iterative decoding process resulting from these considerations is
depicted in algorithm \ref{alg:prox}.
\begin{genericAlgorithm}[caption={Proximal decoding algorithm for an \ac{AWGN} channel.
Based on Algorithm 1 in \protect\cite{proximal_paper}},
label={alg:prox}]
$\boldsymbol{s} \leftarrow \boldsymbol{0}$
for $K$ iterations do
$\boldsymbol{r} \leftarrow \boldsymbol{s} - \omega \left( \boldsymbol{s} - \boldsymbol{y} \right) $
$\boldsymbol{s} \leftarrow \Pi_\eta \left(\boldsymbol{r} - \gamma \nabla h\left( \boldsymbol{r} \right) \right)$
$\boldsymbol{\hat{x}} \leftarrow \text{sign}\left( \boldsymbol{s} \right) $
if $\boldsymbol{H}\boldsymbol{\hat{c}} = \boldsymbol{0}$ do
return $\boldsymbol{\hat{c}}$
end if
end for
return $\boldsymbol{\hat{c}}$
\end{genericAlgorithm}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%\section{Implementation Details}%
%\label{sec:prox:Implementation Details}
The algorithm was first implemented in Python because of the fast development
process and straightforward debugging ability.
It was subsequently reimplemented in C++ using the Eigen%
\footnote{\url{https://eigen.tuxfamily.org}}
linear algebra library to achieve higher performance.
The focus has been on a fast implementation, sometimes at the expense of
memory usage, somewhat limiting the size of the codes the implementation can be
used with.
The evaluation of decoding operations and subsequent calculation of \acp{BER},
\acp{FER}, etc., has been wholly realized in Python.
Concerning the proximal decoding algorithm itself, there are certain aspects
presenting optimization opportunities during the implementation.
The gradient of the code-constraint polynomial \cite[Sec. 2.3]{proximal_paper}, for example,
is given by%
%
\begin{align*}
\nabla h\left( \tilde{\boldsymbol{x}} \right) &= \begin{bmatrix}
\frac{\partial}{\partial \tilde{x}_1}h\left( \tilde{\boldsymbol{x}} \right) &
\ldots &
\frac{\partial}{\partial \tilde{x}_n}h\left( \tilde{\boldsymbol{x}} \right) &
\end{bmatrix}^\text{T}, \\[1em]
\frac{\partial}{\partial \tilde{x}_k}h\left( \tilde{\boldsymbol{x}} \right)
&= 4\left( \tilde{x}_k^2 - 1 \right) \tilde{x}_k
+ \frac{2}{\tilde{x}_k} \sum_{j\in N_v\left( k \right) }\left(
\left( \prod_{i \in N_c\left( j \right)} \tilde{x}_i \right)^2
- \prod_{i\in N_c\left( j \right) } \tilde{x}_i \right)
.\end{align*}
%
Since the products
$\prod_{i\in N_c\left( j \right) } \tilde{x}_i,\hspace{2mm}j\in \mathcal{J}$
are identical for all components $\tilde{x}_k$ of $\tilde{\boldsymbol{x}}$, they can be
precomputed.
Defining%
%
\begin{align*}
\boldsymbol{p} := \begin{bmatrix}
\prod_{i\in N_c\left( 1 \right) } \tilde{x}_i \\
\vdots \\
\prod_{i\in N_c\left( m \right) } \tilde{x}_i \\
\end{bmatrix}
\hspace{5mm}
\text{and}
\hspace{5mm}
\boldsymbol{v} := \boldsymbol{p}^{\circ 2} - \boldsymbol{p}
,\end{align*}
%
the gradient can be written as%
%
\begin{align*}
\nabla h\left( \tilde{\boldsymbol{x}} \right) =
4\left( \tilde{\boldsymbol{x}}^{\circ 3} - \tilde{\boldsymbol{x}} \right)
+ 2\tilde{\boldsymbol{x}}^{\circ \left( -1 \right) } \circ \boldsymbol{H}^\text{T}
\boldsymbol{v}
,\end{align*}
%
enabling its computation primarily with element-wise operations and
matrix-vector multiplication.
This is beneficial, as the libraries employed for the implementation are
heavily optimized for such calculations (e.g., through vectorization of the
operations).
The projection $\prod_{\eta}\left( . \right)$ also proves straightforward to
compute, as it amounts to simply clipping each component of the vector onto
$[-\eta, \eta]$ individually.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Analysis and Simulation Results}%
\label{sec:prox:Analysis and Simulation Results}
In this section, the general behavior of the proximal decoding algorithm is
analyzed.
The impact of the parameters $\gamma$, as well as $\omega$, the maximum
number of iterations $K$ and $\eta$ is examined.
The decoding performance is assessed based on the \ac{BER} and the
\ac{FER} as well as the \textit{decoding failure rate} - the rate at which
the algorithm produces results that are not valid codewords.
The convergence properties are reviewed and related to the decoding
performance.
Finally, the computational performance is examined on a theoretical basis
as well as on the basis of the implementation completed in the context of this
thesis.
All simulation results presented hereafter are based on Monte Carlo
simulations.
The \ac{BER} and \ac{FER} curves in particular have been generated by
producing at least 100 frame errors for each data point, unless otherwise
stated.
\subsection{Choice of Parameters}
\label{subsec:prox:choice}
First, the effect of the parameter $\gamma$ is investigated.
Figure \ref{fig:prox:results} shows a comparison of the decoding performance
of the proximal decoding algorithm as presented by Wadayama et al.
\cite{proximal_paper} and the implementation realized for this work.
\noindent The \ac{BER} curves for three different choices of
$\gamma$ are shown, as well as the curve resulting from decoding
using a \ac{BP} decoder, as a reference.
The results from Wadayama et al. are shown with solid lines,
while the newly generated ones are shown with dashed lines.
The parameters chosen are $K=200, \mu = 0.05$ and $\eta=1.5$.
It is noticeable that for a moderately chosen value of $\gamma$
%
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[grid=both, grid style={line width=.1pt},
xlabel={$E_b / N_0$ (dB)}, ylabel={BER},
ymode=log,
legend style={at={(0.5,-0.7)},anchor=south},
legend cell align={left},
width=0.6\textwidth,
height=0.45\textwidth,
ymax=1.2, ymin=0.8e-4,
xtick={1, 2, ..., 5},
xmin=0.9, xmax=5.6,
legend columns=2,]
\addplot [ForestGreen, mark=*, line width=1pt]
table [x=SNR, y=gamma_0_15, col sep=comma] {res/proximal/ber_paper.csv};
\addlegendentry{$\gamma = 0.15$ (Wadayama et al.)}
\addplot [ForestGreen, mark=triangle, dashed, line width=1pt]
table [x=SNR, y=BER, col sep=comma,
discard if not={gamma}{0.15},
discard if gt={SNR}{5.5},]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.15$ (Own results)}
\addplot [NavyBlue, mark=*, line width=1pt]
table [x=SNR, y=gamma_0_01, col sep=comma] {res/proximal/ber_paper.csv};
\addlegendentry{$\gamma = 0.01$ (Wadayama et al.)}
\addplot [NavyBlue, mark=triangle, dashed, line width=1pt]
table [x=SNR, y=BER, col sep=comma,
discard if not={gamma}{0.01},
discard if gt={SNR}{5.5},]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.01$ (Own results)}
\addplot [RedOrange, mark=*, line width=1pt]
table [x=SNR, y=gamma_0_05, col sep=comma] {res/proximal/ber_paper.csv};
\addlegendentry{$\gamma = 0.05$ (Wadayama et al.)}
\addplot [RedOrange, mark=triangle, dashed, line width=1pt]
table [x=SNR, y=BER, col sep=comma,
discard if not={gamma}{0.05},
discard if gt={SNR}{5.5},]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.05$ (Own results)}
\addplot [RoyalPurple, mark=*, line width=1pt]
table [x=SNR, y=BER, col sep=comma,
discard if gt={SNR}{3.5}]
{res/generic/bp_20433484.csv};
\addlegendentry{BP (200 iterations)}
\end{axis}
\end{tikzpicture}
\caption{Comparison of datapoints from Wadayama et al. with own simulation results.
(3, 6) regular \ac{LDPC} code with $n=204, k=102$ \cite[\text{204.33.484}]{mackay_enc}}
\label{fig:prox:results}
\end{figure}
%
($\gamma = 0.05$) the decoding performance is better than for low
($\gamma = 0.01$) or high ($\gamma = 0.15$) values.
The question arises whether there is some optimal value maximizing the decoding
performance, especially since it seems to dramatically depend on $\gamma$.
To better understand how they are
related, figure \ref{fig:prox:results} was recreated, but with a considerably
larger selection of values for $\gamma$.
In this new graph, shown in figure \ref{fig:prox:results_3d}, instead of
stacking the \ac{BER} curves on top of one another in the same plot, the
visualization is extended to three dimensions.
The previously shown results are highlighted.
Evidently, while the decoding performance does depend on the value of
$\gamma$, there is no single optimal value offering optimal performance, but
rather a certain interval in which it stays largely unchanged.
This indicates that while the choice of the parameter $\gamma$
significantly affects the decoding performance, there is not much benefit
attainable in undertaking an extensive search for an exact optimum.
Rather, a preliminary examination providing a rough window for $\gamma$ may
be sufficient.
Similar results can be observed when comparing several different codes, as
shown in figure \ref{fig:prox:results_3d_multiple}.
It is apparent that while the exact landscape of the graph depends on the code,
the general behavior is the same for all codes analyzed in this thesis.
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[view={75}{30},
zmode=log,
xlabel={$E_b / N_0$ (dB)},
ylabel={$\gamma$},
zlabel={BER},
legend pos=outer north east,
%legend style={at={(0.5,-0.7)},anchor=south},
ytick={0, 0.05, 0.1, 0.15},
width=0.6\textwidth,
height=0.45\textwidth,]
\addplot3[surf,
mesh/rows=17, mesh/cols=14,
colormap/viridis] table [col sep=comma,
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = \left[ 0\text{:}0.01\text{:}0.16 \right] $}
\addplot3[NavyBlue, line width=1.5] table [col sep=comma,
discard if not={gamma}{0.01},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.01$}
\addplot3[RedOrange, line width=1.5] table [col sep=comma,
discard if not={gamma}{0.05},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.05$}
\addplot3[ForestGreen, line width=1.5] table [col sep=comma,
discard if not={gamma}{0.15},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.15$}
\end{axis}
\end{tikzpicture}
\caption{Visualization of the relationship between the decoding performance
and the parameter $\gamma$. (3,6) regular \ac{LDPC} code with
$n=204, k=102$ \cite[\text{204.33.484}]{mackay_enc}}
\label{fig:prox:results_3d}
\end{figure}%
The parameter $\gamma$ describes the step-size for the optimization step
dealing with the code-constraint polynomial;
the parameter $\omega$ describes the step-size for the step dealing with the
negative-log likelihood.
The relationship between $\omega$ and $\gamma$ is portrayed in figure
\ref{fig:prox:gamma_omega}.
The color of each cell indicates the \ac{BER} when the corresponding values
are chosen for the decoding.
The \ac{SNR} is kept constant at $\SI{4}{dB}$.
The \ac{BER} exhibits similar behavior in its dependency on $\omega$ and
on $\gamma$: it is minimized when keeping the value within certain
bounds, without displaying a single distinct optimum.
It is noteworthy that the decoder seems to achieve the best performance for
similar values of the two step sizes.
Again, this consideration applies to a multitude of different codes, as
depicted in figure \ref{fig:prox:gamma_omega_multiple}.
To better understand how to determine the optimal value for the parameter $K$,
the average error is inspected.
This time $\gamma$ and $\omega$ are held constant at $0.05$ and the average
error is observed during each iteration of the decoding process, for several
different \acp{SNR}.
The plots have been generated by averaging the error over $\SI{500000}{}$
decodings.%
%
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[
colormap/viridis,
colorbar,
xlabel={$\omega$}, ylabel={$\gamma$},
at={(0,0)}, view={0}{90},
zmode=log,
ytick={0, 0.05, 0.1, 0.15},
yticklabels={0, 0.05, 0.1, 0.15},
xtick={0.05, 0.1, 0.15, 0.2},
xticklabels={0.05, 0.1, 0.15, 0.2},
width=0.56\textwidth,
height=0.42\textwidth,
point meta min=-5.7,
point meta max=-0.5,
colorbar style={
title={\acs{BER}},
ytick={-5,-4,...,-1},
yticklabels={$10^{-5}$,$10^{-4}$,$10^{-3}$,$10^{-2}$,$10^{-1}$}
}]
]
\addplot3[
surf,
shader=flat,
mesh/rows=17, mesh/cols=10,
]
table [col sep=comma, x=omega, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_gamma_omega_20433484.csv};
\end{axis}
\end{tikzpicture}
\caption{The \ac{BER} as a function of the two step sizes. (3,6) regular
\ac{LDPC} code with $n=204, k=102$ \cite[\text{204.33.484}]{mackay_enc}}
\label{fig:prox:gamma_omega}
\end{figure}%
%
As some decodings go on for more iterations than others, the number of values
which are averaged for each datapoints vary.
This explains the dip visible in all curves around the 20th iteration, since
after this point more and more correct decodings are completed,
leaving more and more faulty ones to be averaged.
Additionally, at this point the decline in the average error stagnates,
rendering an increase in $K$ counterproductive as it only raises the average
timing requirements of the decoding process.
Another aspect to consider is that the higher the \ac{SNR}, the fewer
decodings are present at each iteration
to average, since a solution is found earlier.
This explains the decreasing smoothness of the lines as the \ac{SNR} increases.
Remarkably, the \ac{SNR} seems to not have any impact on the number of
iterations necessary to reach the point at which the average error
stabilizes.
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
ylabel={Average $\lVert \boldsymbol{c}-\boldsymbol{\hat{c}} \rVert$},
legend pos=outer north east,
width=0.6\textwidth,
height=0.45\textwidth,
]
\addplot [ForestGreen, mark=none, line width=1pt]
table [col sep=comma, discard if not={omega}{0.0774263682681127}, x=k, y=err]
{res/proximal/2d_avg_error_20433484_1db.csv};
\addlegendentry{$E_b / N_0 = \SI{1}{dB}$}
\addplot [NavyBlue, mark=none, line width=1pt]
table [col sep=comma, discard if not={omega}{0.0774263682681127}, x=k, y=err]
{res/proximal/2d_avg_error_20433484_3db.csv};
\addlegendentry{$E_b / N_0 = \SI{3}{dB}$}
\addplot [RedOrange, mark=none, line width=1pt]
table [col sep=comma, discard if not={omega}{0.052233450742668434}, x=k, y=err]
{res/proximal/2d_avg_error_20433484_5db.csv};
\addlegendentry{$E_b / N_0 = \SI{5}{dB}$}
\addplot [RoyalPurple, mark=none, line width=1pt]
table [col sep=comma, discard if not={omega}{0.052233450742668434}, x=k, y=err]
{res/proximal/2d_avg_error_20433484_8db.csv};
\addlegendentry{$E_b / N_0 = \SI{8}{dB}$}
\end{axis}
\end{tikzpicture}
\caption{Average error for $\SI{500000}{}$ decodings. (3,6) regular \ac{LDPC} code
with $n=204, k=102$ \cite[\text{204.33.484}]{mackay_enc}}
\end{figure}%
Changing the parameter $\eta$ does not appear to have a significant effect on
the decoding performance when keeping the value within a reasonable window
(``slightly larger than one'', as stated in \cite[Sec. 3.2]{proximal_paper}),
which seems plausible considering its only function is ensuring numerical stability.
Summarizing the above considerations, an intricate strategy to find the exact
optimum values for the parameters $\gamma$ and $\omega$ appears to bring
limited benefit;
an initial rudimentary examination to find the general bounds in which the two
values should lie is sufficient.
The parameter $K$ is independent of the \ac{SNR} and raising its value above a
certain threshold does not improve the decoding performance.
The choice of $\eta$ is insignificant and the parameter is only relevant as a
means to bring about numerical stability.
\subsection{Decoding Performance}
Until now, only the \ac{BER} has been considered to gauge the decoding
performance.
The \ac{FER}, however, shows considerably different behavior, as can be seen in
figure \ref{fig:prox:ber_fer_dfr}.
Besides the \ac{BER} and \ac{FER} curves, the figure also shows the
\textit{decoding failure rate}.
This is the rate at which the iterative process produces invalid codewords,
i.e., the stopping criterion (line 6 of algorithm \ref{alg:prox}) is never
satisfied and the maximum number of iterations $K$ is reached without
converging to a valid codeword.
Three lines are plotted in each case, corresponding to different values of
the parameter $\gamma$.
The values chosen are the same as in figure \ref{fig:prox:results}, as they
seem to adequately describe the behavior across a wide range of values
(see figure \ref{fig:prox:results_3d}).
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={BER},
ymode=log,
width=0.48\textwidth,
height=0.36\textwidth,
legend style={at={(0.05,0.05)},anchor=south west},
ymax=1.5, ymin=3e-7,]
\addplot [ForestGreen, mark=*]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.15$}
\addplot [NavyBlue, mark=*]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.01$}
\addplot [RedOrange, mark=*]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.05$}
\end{axis}
\end{tikzpicture}%
\hfill%
\begin{tikzpicture}
\begin{axis}[grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
width=0.48\textwidth,
height=0.36\textwidth,
legend style={at={(0.05,0.05)},anchor=south west},
ymax=1.5, ymin=3e-7,]
\addplot [ForestGreen, mark=*]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.15$}
\addplot [NavyBlue, mark=*]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.01$}
\addplot [RedOrange, mark=*]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.05$}
\end{axis}
\end{tikzpicture}\\[1em]
\begin{tikzpicture}
\begin{axis}[grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={Decoding Failure Rate},
ymode=log,
width=0.48\textwidth,
height=0.36\textwidth,
legend style={at={(0.05,0.05)},anchor=south west},
ymax=1.5, ymin=3e-7,]
\addplot [ForestGreen, mark=*]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.15$}
\addplot [NavyBlue, mark=*]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.01$}
\addplot [RedOrange, mark=*]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addlegendentry{$\gamma = 0.05$}
\end{axis}
\end{tikzpicture}
\caption{Comparison of \ac{FER}, \ac{BER} and decoding failure rate. (3,6) regular
\ac{LDPC} code with $n=204, k=102$ \cite[\text{204.33.484}]{mackay_enc}}
\label{fig:prox:ber_fer_dfr}
\end{figure}%
It is apparent that the \ac{FER} and the decoding failure rate are extremely
similar, especially for higher \acp{SNR}.
This leads to the hypothesis that, at least for higher \acp{SNR}, frame errors
arise mainly due to the non-convergence of the algorithm instead of
convergence to the wrong codeword.
This course of thought will be picked up in section
\ref{sec:prox:Improved Implementation} when proposing a method to improve the
algorithm.
In summary, the \ac{BER} and \ac{FER} indicate dissimilar decoding
performance.
The decoding failure rate closely resembles the \ac{FER}, suggesting that
the frame errors may largely be attributed to decoding failures.
\subsection{Convergence Properties}
\label{subsec:prox:conv_properties}
The previous observation that the \ac{FER} may arise mainly due to the
non-convergence of the algorithm instead of convergence to the wrong codeword,
raises the question why the decoding process does not converge so often.
To better understand this issue, the iterative process is visualized in
figure \ref{fig:prox:convergence}.
In order to be able to simultaneously consider all components of the vectors
being dealt with, a BCH code with $n=7$ and $k=4$ is chosen.
Each plot shows one component of the current estimate during a given
iteration ($\boldsymbol{r}$ and $\boldsymbol{s}$ are counted as different
estimates and their values are interwoven to obtain the shown result), as well
as the gradients of the negative log-likelihood and the code-constraint
polynomial, which influence the next estimate.
%
\begin{figure}[H]
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.9\textwidth,
height=0.3\textwidth,
scale only axis,
xtick={0, 50, ..., 200},
xticklabels={0, 25, ..., 100},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_1]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_1]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_1]
{res/proximal/comp_bch_7_4_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L \right)_2$}
\addlegendentry{$\left(\nabla h \right)_2 $}
\end{axis}
\end{tikzpicture}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.9\textwidth,
height=0.3\textwidth,
scale only axis,
xtick={0, 50, ..., 200},
xticklabels={0, 25, ..., 100},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_2]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_2]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_2]
{res/proximal/comp_bch_7_4_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L \right)_3$}
\addlegendentry{$\left(\nabla h \right)_3 $}
\end{axis}
\end{tikzpicture}
\end{subfigure}%
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.9\textwidth,
height=0.3\textwidth,
scale only axis,
xtick={0, 50, ..., 200},
xticklabels={0, 25, ..., 100},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_3]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_3]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_3]
{res/proximal/comp_bch_7_4_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L \right)_4$}
\addlegendentry{$\left(\nabla h \right)_4 $}
\end{axis}
\end{tikzpicture}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.9\textwidth,
height=0.3\textwidth,
scale only axis,
xtick={0, 50, ..., 200},
xticklabels={0, 25, ..., 100},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_4]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_4]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_4]
{res/proximal/comp_bch_7_4_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L \right)_5$}
\addlegendentry{$\left(\nabla h \right)_5 $}
\end{axis}
\end{tikzpicture}
\end{subfigure}%
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.9\textwidth,
height=0.3\textwidth,
scale only axis,
xtick={0, 50, ..., 200},
xticklabels={0, 25, ..., 100},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_5]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_5]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_5]
{res/proximal/comp_bch_7_4_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L \right)_6$}
\addlegendentry{$\left(\nabla h \right)_6 $}
\end{axis}
\end{tikzpicture}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.9\textwidth,
height=0.3\textwidth,
scale only axis,
xtick={0, 50, ..., 200},
xticklabels={0, 25, ..., 100},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_6]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_6]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_6]
{res/proximal/comp_bch_7_4_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L \right)_7$}
\addlegendentry{$\left(\nabla h \right)_7 $}
\end{axis}
\end{tikzpicture}
\end{subfigure}
\vspace{5mm}
\begin{subfigure}[t]{\textwidth}
\centering
\begin{tikzpicture}[spy using outlines={circle, magnification=6,
connect spies}]
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.6\textwidth,
height=0.225\textwidth,
scale only axis,
xtick={0, 50, ..., 200},
xticklabels={0, 25, ..., 100},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_0]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_0]
{res/proximal/comp_bch_7_4_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_0]
{res/proximal/comp_bch_7_4_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L \right)_1$}
\addlegendentry{$\left(\nabla h \right)_1 $}
\coordinate (spypoint) at (axis cs:100,1.11);
\coordinate (magnifyglass) at (axis cs:-75,0);
\end{axis}
\spy [black, size=2cm] on (spypoint)
in node[fill=white] at (magnifyglass);
\end{tikzpicture}
\end{subfigure}
\caption{Visualization of a single decoding operation. BCH$\left( 7, 4 \right)$ code}
\label{fig:prox:convergence}
\end{figure}%
%
It is evident that in all cases, past a certain number of
iterations, the estimate starts to oscillate around a particular value.
Jointly, the two gradients stop further approaching the value
zero.
This leads to the two terms of the objective function and in particular the
code-constraint polynomial not being minimized.
As such, the constraints are not being satisfied and the estimate is not
converging towards a valid codeword.
While figure \ref{fig:prox:convergence} shows only one instance of a decoding
task with no statistical significance, it is indicative of the general
behavior of the algorithm.
This can be justified by looking at the gradients themselves.
In figure \ref{fig:prox:gradients} the gradients of the negative
log-likelihood and the code-constraint polynomial for a repetition code with
$n=2$ are shown.
The two valid codewords of the $n=2$ repetition code can be recognized in
figure \ref{fig:prox:gradients:h} as
$\boldsymbol{c}_1 = \begin{bmatrix} -1 & -1 \end{bmatrix} $ and
$\boldsymbol{c}_2 = \begin{bmatrix} 1 & 1 \end{bmatrix}$;
these are also the points producing the global minima of the code-constraint
polynomial.
The gradient of the negative log-likelihood points towards the received
codeword as can be seen in figure \ref{fig:prox:gradients:L},
since assuming \ac{AWGN} and no other information that is the
estimate maximizing the likelihood.
Looking at figure \ref{fig:prox:gradients:h} it also becomes apparent why the
value of the parameter $\gamma$ has to be kept small, as mentioned in section
\ref{sec:prox:Decoding Algorithm}.
Local minima are introduced between the codewords, in the areas in which it is
not immediately clear which codeword is the most likely one.
Increasing the value of $\gamma$ results in
$h \left( \tilde{\boldsymbol{x}} \right)$ dominating the landscape of the
objective function, thereby introducing these local minima into the objective
function.
\begin{figure}[H]
\centering
\begin{subfigure}[c]{0.5\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[xmin = -1.25, xmax=1.25,
ymin = -1.25, ymax=1.25,
xlabel={$x_1$}, ylabel={$x_2$},
width=\textwidth,
height=0.75\textwidth,
grid=major, grid style={dotted},
view={0}{90}]
\addplot3[point meta=\thisrow{grad_norm},
point meta min=1,
point meta max=3,
quiver={u=\thisrow{grad_0},
v=\thisrow{grad_1},
scale arrows=.05,
every arrow/.append style={%
line width=.3+\pgfplotspointmetatransformed/1000,
-{Latex[length=0pt 5,width=0pt 3]}
},
},
quiver/colored = {mapped color},
colormap/rocket,
-stealth,
]
table[col sep=comma] {res/proximal/2d_grad_L.csv};
\end{axis}
\end{tikzpicture}
\caption{$\nabla L \left(\boldsymbol{y} \mid \tilde{\boldsymbol{x}} \right) $
for a repetition code with $n=2$}
\label{fig:prox:gradients:L}
\end{subfigure}%
\hfill%
\begin{subfigure}[c]{0.5\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[xmin = -1.25, xmax=1.25,
ymin = -1.25, ymax=1.25,
xlabel={$x_1$}, ylabel={$x_2$},
grid=major, grid style={dotted},
width=\textwidth,
height=0.75\textwidth,
view={0}{90}]
\addplot3[point meta=\thisrow{grad_norm},
point meta min=1,
point meta max=4,
quiver={u=\thisrow{grad_0},
v=\thisrow{grad_1},
scale arrows=.03,
every arrow/.append style={%
line width=.3+\pgfplotspointmetatransformed/1000,
-{Latex[length=0pt 5,width=0pt 3]}
},
},
quiver/colored = {mapped color},
colormap/rocket,
-stealth,
]
table[col sep=comma] {res/proximal/2d_grad_h.csv};
\end{axis}
\end{tikzpicture}
\caption{$\nabla h \left( \tilde{\boldsymbol{x}} \right) $
for a repetition code with $n=2$}
\label{fig:prox:gradients:h}
\end{subfigure}%
\caption{Gradiensts of the negative log-likelihood and the code-constraint
polynomial}
\label{fig:prox:gradients}
\end{figure}%
It is obvious that walking along the gradients in an alternating fashion will
produce a net movement in a certain direction, as long as they
have a common component.
As soon as this common component is exhausted, they will start pulling the
estimate in opposing directions, leading to an oscillation as illustrated
in figure \ref{fig:prox:convergence}.
Consequently, this oscillation is an intrinsic property of the structure of
the minimization process of the proximal decoding algorithm,
where the two parts of the objective function
are minimized in an alternating fashion by use of their gradients.
While the initial net movement is generally directed in the right direction
owing to the gradient of the negative log-likelihood, the resulting oscillation
may well take place in a segment of space not corresponding to a valid
codeword, leading to the aforementioned non-convergence of the algorithm.
This also partly explains the difference in decoding performance when looking
at the \ac{BER} and \ac{FER}, as it would lower the amount of bit errors while
still yielding an invalid codeword.
The higher the \ac{SNR}, the more likely the gradient of the negative
log-likelihood is to point to a valid codeword.
The common component of the two gradients then pulls the estimate closer to
a valid codeword before the oscillation takes place.
This explains why the decoding performance is significantly better for higher
\acp{SNR}.
When considering codes with larger $n$ the behavior generally stays the
same, with some minor differences.
In figure \ref{fig:prox:convergence_large_n} the decoding process is
visualized for one component of a code with $n=204$, for a single decoding.
The two gradients still eventually oppose each other and the estimate still
starts to oscillate, the same as illustrated in figure
\ref{fig:prox:convergence} based on a code with $n=7$.
However, in this case, the gradient of the code-constraint polynomial itself
starts to oscillate, its average value being such that the effect of the
gradient of the negative log-likelihood is counteracted.
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={Iterations},
width=0.6\textwidth,
height=0.225\textwidth,
scale only axis,
xtick={0, 100, ..., 400},
xticklabels={0, 50, ..., 200},
]
\addplot [NavyBlue, mark=none, line width=1]
table [col sep=comma, x=k, y=comb_r_s_0]
{res/proximal/extreme_components_20433484_combined.csv};
\addplot [ForestGreen, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_L_0]
{res/proximal/extreme_components_20433484_combined.csv};
\addplot [RedOrange, mark=none, line width=1]
table [col sep=comma, x=k, y=grad_h_0]
{res/proximal/extreme_components_20433484_combined.csv};
\addlegendentry{est}
\addlegendentry{$\left(\nabla L\right)_1$}
\addlegendentry{$\left(\nabla h\right)_1$}
\end{axis}
\end{tikzpicture}
\caption{Visualization of a single decoding operation. (3,6) regular \ac{LDPC} code
with $n=204, k=102$ \cite[\text{204.33.484}]{mackay_enc}}
\label{fig:prox:convergence_large_n}
\end{figure}%
In conclusion, as a general rule, the proximal decoding algorithm reaches
an oscillatory state which it cannot escape as a consequence of its structure.
In this state the constraints may not be satisfied, leading to the algorithm
exhausting its maximum number of iterations without converging and returning
an invalid codeword.
\subsection{Computational Performance}
\label{subsec:prox:comp_perf}
In order to determine the time complexity of proximal decoding for an
\ac{AWGN} channel, the decoding process as depicted in algorithm
\ref{alg:prox} is considered.
When dealing with \ac{LDPC} codes, i.e., the number of non-zero entries in the
parity-check matrix $\boldsymbol{H}$ grows linearly
with $n$, the two
recursive steps in lines 3 and 4 have time complexity
$\mathcal{O}\left( n \right)$ \cite[Sec. 4.1]{proximal_paper}.
The $\text{sign}$ operation in line 5 also has $\mathcal{O}\left( n \right) $
time complexity, as it only depends on the $n$ components of $\boldsymbol{s}$.
Given the sparsity of the matrix $\boldsymbol{H}$, evaluating the parity-check
condition has linear time complexity as well, since at most $n$ additions and
multiplications have to be performed.
This means that the overall time complexity of proximal decoding for \ac{LDPC}
codes in an \ac{AWGN} channel is $\mathcal{O}\left( n \right)$, which is
practical since it is the same as that of $\ac{BP}$.
This theoretical analysis is also corroborated by the practical results shown
in figure \ref{fig:prox:time_comp}.
The codes considered are the BCH(31, 11) and BCH(31, 26) codes, several (3, 6)
regular \ac{LDPC} codes (\cite[\text{96.3.965, 204.33.484, 408.33.844}]{mackay_enc}),
a (5,10) regular \ac{LDPC} code (\cite[\text{204.55.187}]{mackay_enc}) and a
progressive edge growth construction code (\cite[\text{PEGReg252x504}]{mackay_enc}).
Some deviations from linear behavior are unavoidable, since not all codes
considered are actually \ac{LDPC} codes, or \ac{LDPC} codes constructed
according to the same scheme.
Nonetheless, a generally linear relationship between the average time needed to
decode a received frame and the length $n$ of the frame can be observed.
These results were generated on an Intel Core i7-7700HQ 4-core CPU, running at
$\SI{2.80}{GHz}$ and utilizing all cores.
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[grid=both,
xlabel={$n$}, ylabel={Time per frame (s)},
width=0.6\textwidth,
height=0.45\textwidth,
legend cell align={left},]
\addplot[RedOrange, only marks, mark=square*]
table [col sep=comma, x=n, y=spf]
{res/proximal/fps_vs_n.csv};
\end{axis}
\end{tikzpicture}
\caption{Timing requirements of the proximal decoding implementation}
\label{fig:prox:time_comp}
\end{figure}%
%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Improved Implementation}%
\label{sec:prox:Improved Implementation}
As mentioned earlier, frame errors seem to mainly stem from decoding failures.
Coupled with the fact that the \ac{BER} indicates significantly better
performance than the \ac{FER}, this leads to the assumption that only a small
number of components of the estimated vector may be responsible for an invalid
result.
If it was possible to limit the number of possibly wrong components of the
estimate to a small subset, an \ac{ML}-decoding step could be performed on
a limited number of possible results (``ML-in-the-list'', as it is called)
to improve the decoding performance.
This concept is pursued in this section.
First, a guideline must be found with which to evaluate the probability that
a given component of an estimate is wrong.
One compelling observation is that the closer an estimate is to being at a
valid codeword, the smaller the magnitude of the gradient of the
code-constraint polynomial, as illustrated in figure \ref{fig:prox:gradients}.
This gives rise to the notion that some property or behavior of
$\nabla h\left( \tilde{\boldsymbol{x}} \right) $ may be related in its
magnitude to the confidence that a given bit is correct.
And indeed, the magnitude of the oscillation of
$\nabla h\left( \tilde{\boldsymbol{x}} \right)$ (introduced previously in
section \ref{subsec:prox:conv_properties} and shown in figure
\ref{fig:prox:convergence_large_n}) and the probability of having a bit
error are strongly correlated, a relationship being depicted in figure
\ref{fig:prox:correlation}.
The x-axis depicts the variance in $\nabla h\left( \tilde{\boldsymbol{x}} \right)$
after the 100th iteration, and the y-axis depicts whether there is a bit error.
While this is not exactly the magnitude of the oscillation, it is
proportional and easier to compute.
The datapoints are taken from a single decoding operation.
Using this observation as a rule to determine the $N\in\mathbb{N}$ most
probably wrong bits, all variations of the estimate with those bits modified
can be generated.
An \ac{ML}-in-the-list step can then be performed to determine the
most likely candidate.
This process is outlined in algorithm \ref{alg:prox:improved}.
Its only difference to algorithm \ref{alg:prox} is that instead of returning
the last estimate when no valid result is reached, an ML-in-the-list step is
performed.
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[point meta min = -1,
point meta max = 1,
grid=both,
xlabel={$Var\left( \nabla h\left( \tilde{\boldsymbol{x}} \right) \right) $},
ylabel={Bit error (bool)},
ytick={0, 1},
width=8cm,
height=3cm,
%colormap/viridis,
scale only axis,]
\addplot [RoyalPurple, only marks,]
table [col sep=comma, x=grad_h_vars, y=bit_error]
{res/proximal/extreme_components_20433484_variance.csv};
\end{axis}
\end{tikzpicture}
\caption{Correlation between the occurrence of a bit error and the
amplitude of oscillation of the gradient of the code-constraint polynomial.
(3,6) regular \ac{LDPC} code with $n=204, k=102$ \cite[\text{204.33.484}]{mackay_enc}}
\label{fig:prox:correlation}
\end{figure}%
\begin{genericAlgorithm}[caption={Improved proximal decoding algorithm},
label={alg:prox:improved},]
$\boldsymbol{s} \leftarrow \boldsymbol{0}$
for $K$ iterations do
$\boldsymbol{r} \leftarrow \boldsymbol{s} - \omega \nabla L \left( \boldsymbol{y} \mid \boldsymbol{s} \right) $
$\boldsymbol{s} \leftarrow \boldsymbol{r} - \gamma \nabla h\left( \boldsymbol{r} \right) $
$\boldsymbol{\hat{x}} \leftarrow \text{sign}\left( \boldsymbol{s} \right) $
if $\boldsymbol{H}\boldsymbol{\hat{c}} = \boldsymbol{0}$
return $\boldsymbol{\hat{c}}$
end if
end for
$\textcolor{KITblue}{\text{Find }N\text{ most probably wrong bits}}$
$\textcolor{KITblue}{\text{Generate variations } \hat{\boldsymbol{c}}_l,\hspace{1mm}
l=1,\ldots,2^N\text{ of } \hat{\boldsymbol{c}}\text{ with the }N\text{ bits modified}}$
$\textcolor{KITblue}{\text{Compute }d_H\left( \hat{\boldsymbol{c}}_l,
\hat{\boldsymbol{c}} \right) \text{ for all valid codewords } \hat{\boldsymbol{c}}_l}$
$\textcolor{KITblue}{\text{Output }\hat{\boldsymbol{c}}_l\text{ with lowest }
d_H\left( \hat{\boldsymbol{c}}_l, \hat{\boldsymbol{c}} \right)}$
\end{genericAlgorithm}
Figure \ref{fig:prox:improved_results} shows the gain that can be achieved
when the number $N$ is chosen to be 12.
Again, three values of gamma are chosen, for which the \ac{BER}, \ac{FER}
and decoding failure rate are plotted.
The simulation results for the original proximal decoding algorithm are shown
with solid lines and the results for the improved version are shown with
dashed lines.
For the case of $\gamma = 0.05$, the number of frame errors produced for the
datapoints at $\SI{6}{dB}$, $\SI{6.5}{dB}$ and $\SI{7}{dB}$ are
70, 17 and 2, respectively.
The gain seems to depend on the value of $\gamma$, as well as becoming more
pronounced for higher \ac{SNR} values.
This is to be expected, since with higher \ac{SNR} values the number of bit
errors decreases, making the correction of those errors in the ML-in-the-list
step more likely.
In figure \ref{fig:prox:improved:comp} the decoding performance
between proximal decoding and the improved algorithm is compared for a number
of different codes.
In the case of the code with $n=504$ shown in figure
\ref{fig:prox:improved:comp:504}, only 76 frame errors were produced to
generate the point for the improved algorithm for $\gamma=0.05$ at
$\SI{5.5}{dB}$.
Similar behavior can be observed in all cases, with varying improvement over
standard proximal decoding.
In some cases, a gain of up to $\SI{1}{dB}$ or higher can be achieved.
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={BER},
ymode=log,
width=0.48\textwidth,
height=0.36\textwidth,
ymax=1.5, ymin=3e-8,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=BER, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\end{axis}
\end{tikzpicture}
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
width=0.48\textwidth,
height=0.36\textwidth,
ymax=1.5, ymin=3e-8,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\end{axis}
\end{tikzpicture}
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={Decoding Failure Rate},
ymode=log,
width=0.48\textwidth,
height=0.36\textwidth,
ymax=1.5, ymin=3e-8,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=DFR, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\end{axis}
\end{tikzpicture}
\begin{tikzpicture}
\begin{axis}[hide axis,
xmin=10, xmax=50,
ymin=0, ymax=0.4,
legend columns=3,
legend style={draw=white!15!black,legend cell align=left}]
\addlegendimage{ForestGreen, mark=*, solid}
\addlegendentry{proximal, $\gamma = 0.15$}
\addlegendimage{NavyBlue, mark=*, solid}
\addlegendentry{proximal, $\gamma = 0.01$}
\addlegendimage{RedOrange, mark=*, solid}
\addlegendentry{proximal, $\gamma = 0.05$}
\addlegendimage{Emerald, mark=triangle, densely dashed}
\addlegendentry{improved, $\gamma = 0.15$}
\addlegendimage{RoyalPurple, mark=triangle, densely dashed}
\addlegendentry{improved, $\gamma = 0.01$}
\addlegendimage{red, mark=triangle, densely dashed}
\addlegendentry{improved, $\gamma = 0.05$}
\end{axis}
\end{tikzpicture}
\caption{Comparison of the decoding performance between proximal decoding and the
improved implementation. (3,6) regular \ac{LDPC} code with $n=204, k=102$
\cite[\text{204.33.484}]{mackay_enc}}
\label{fig:prox:improved_results}
\end{figure}
The average run time of the improved algorithm depends on the parameter $N$.
The time complexity, however, does not: it is still linear with respect to $n$.
Interestingly, the improved algorithm does not have a much different average
run time than proximal decoding, because the computationally expensive
ML-in-the-list step is only performed when the
proximal decoding algorithm produces an invalid result, which in absolute
terms happens relatively infrequently.
This is illustrated in figure \ref{fig:prox:time_complexity_comp}, where the
average time needed to decode a single received frame is visualized for
proximal decoding as well as for the improved algorithm.
The same codes as before are considered, i.e., the BCH(31, 11) and BCH(31, 26)
codes, several (3, 6) regular \ac{LDPC} codes
(\cite[\text{96.3.965, 204.33.484, 408.33.844}]{mackay_enc}),
a (5,10) regular \ac{LDPC} code (\cite[\text{204.55.187}]{mackay_enc}) and a
progressive edge growth construction code (\cite[\text{PEGReg252x504}]{mackay_enc}).
It should be noted that some variability in the data is to be expected,
since the timing of the actual simulations depends on a multitude of other
parameters such as the scheduling choices of the operating system as well as
variations in the implementations themselves.
Nevertheless, the empirical data, at least in part, supports the
theoretical considerations.
In conclusion, the decoding performance of proximal decoding can be improved
by appending an ML-in-the-list step when the algorithm does not produce a
valid result.
The gain can in some cases be as high as $\SI{1}{dB}$ and is achievable with
negligible computational performance penalty.
The improvement is mainly noticeable for higher \ac{SNR} values and depends on
the code as well as the chosen parameters.
\begin{figure}[H]
\centering
\begin{tikzpicture}
\begin{axis}[grid=both,
width=0.6\textwidth,
height=0.45\textwidth,
xlabel={$n$}, ylabel={Time per frame (s)},
legend style={at={(0.05,0.77)},anchor=south west},
legend cell align={left},]
\addplot[RedOrange, only marks, mark=square*]
table [col sep=comma, x=n, y=spf]
{res/proximal/fps_vs_n.csv};
\addlegendentry{proximal}
\addplot[Gray, only marks, mark=*]
table [col sep=comma, x=n, y=spf]
{res/hybrid/fps_vs_n.csv};
\addlegendentry{improved ($N = 12$)}
\end{axis}
\end{tikzpicture}
\caption{Comparison of the timing requirements of the implementations of proximal
decoding and the improved algorithm}
\label{fig:prox:time_complexity_comp}
\vspace*{10cm}
\end{figure}
\begin{figure}[H]
\centering
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[view={75}{30},
zmode=log,
xlabel={$E_b / N_0$ (dB)},
ylabel={$\gamma$},
zlabel={BER},
width=\textwidth,
height=0.75\textwidth,]
\addplot3[surf,
mesh/rows=17, mesh/cols=10,
colormap/viridis] table [col sep=comma,
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_963965.csv};
\addplot3[RedOrange, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.05},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_963965.csv};
\addplot3[NavyBlue, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.01},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_963965.csv};
\addplot3[ForestGreen, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.15},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_963965.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=96, k=48$
\cite[\text{96.3.965}]{mackay_enc}}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[view={75}{30},
zmode=log,
xlabel={$E_b / N_0$ (dB)},
ylabel={$\gamma$},
zlabel={BER},
width=\textwidth,
height=0.75\textwidth,]
\addplot3[surf,
mesh/rows=17, mesh/cols=10,
colormap/viridis] table [col sep=comma,
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_bch_31_26.csv};
\addplot3[RedOrange, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.05},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_bch_31_26.csv};
\addplot3[NavyBlue, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.01},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_bch_31_26.csv};
\addplot3[ForestGreen, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.15},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_bch_31_26.csv};
\end{axis}
\end{tikzpicture}
\caption{BCH code with $n=31, k=26$\\[2\baselineskip]}
\end{subfigure}
\vspace{3mm}
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[view={75}{30},
zmode=log,
xlabel={$E_b/N_0$ (dB)},
ylabel={$\gamma$},
zlabel={BER},
width=\textwidth,
height=0.75\textwidth,]
\addplot3[surf,
mesh/rows=17, mesh/cols=10,
colormap/viridis] table [col sep=comma,
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484_fewer_SNR.csv};
\addplot3[RedOrange, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.05},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484_fewer_SNR.csv};
\addplot3[NavyBlue, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.01},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484_fewer_SNR.csv};
\addplot3[ForestGreen, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.15},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20433484_fewer_SNR.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=204, k=102$
\cite[\text{204.33.484}]{mackay_enc}}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[view={75}{30},
zmode=log,
xlabel={$E_b / N_0$ (dB)},
ylabel={$\gamma$},
zlabel={BER},
width=\textwidth,
height=0.75\textwidth,]
\addplot3[surf,
mesh/rows=17, mesh/cols=10,
colormap/viridis] table [col sep=comma,
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20455187.csv};
\addplot3[RedOrange, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.05},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20455187.csv};
\addplot3[NavyBlue, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.01},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20455187.csv};
\addplot3[ForestGreen, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.15},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_20455187.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 5, 10 \right)$-regular \ac{LDPC} code with $n=204, k=102$
\cite[\text{204.55.187}]{mackay_enc}}
\end{subfigure}%
\vspace{3mm}
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[view={75}{30},
zmode=log,
xlabel={$E_b / N_0$ (dB)},
ylabel={$\gamma$},
zlabel={BER},
width=\textwidth,
height=0.75\textwidth,]
\addplot3[surf,
mesh/rows=17, mesh/cols=10,
colormap/viridis] table [col sep=comma,
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_40833844.csv};
\addplot3[RedOrange, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.05},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_40833844.csv};
\addplot3[NavyBlue, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.01},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_40833844.csv};
\addplot3[ForestGreen, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.15},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_40833844.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=408, k=204$
\cite[\text{408.33.844}]{mackay_enc}}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[view={75}{30},
zmode=log,
xlabel={$E_b / N_0$ (dB)},
ylabel={$\gamma$},
zlabel={BER},
width=\textwidth,
height=0.75\textwidth,]
\addplot3[surf,
mesh/rows=17, mesh/cols=10,
colormap/viridis] table [col sep=comma,
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot3[RedOrange, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.05},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot3[NavyBlue, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.01},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot3[ForestGreen, line width=1.5] table[col sep=comma,
discard if not={gamma}{0.15},
x=SNR, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_pegreg252x504.csv};
\end{axis}
\end{tikzpicture}
\caption{LDPC code (progressive edge growth construction) with $n=504, k=252$
\cite[\text{PEGReg252x504}]{mackay_enc}}
\end{subfigure}%
\vspace{5mm}
\begin{subfigure}[t]{\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[hide axis,
xmin=10, xmax=50,
ymin=0, ymax=0.4,
legend style={draw=white!15!black,legend cell align=left}]
\addlegendimage{surf, colormap/viridis}
\addlegendentry{$\gamma = \left[ 0\text{ : }0.01\text{ : }0.16 \right] $};
\addlegendimage{NavyBlue, line width=1.5pt}
\addlegendentry{$\gamma = 0.01$};
\addlegendimage{RedOrange, line width=1.5pt}
\addlegendentry{$\gamma = 0.05$};
\addlegendimage{ForestGreen, line width=1.5pt}
\addlegendentry{$\gamma = 0.15$};
\end{axis}
\end{tikzpicture}
\end{subfigure}
\caption{Dependence of the \ac{BER} on the value of the parameter $\gamma$ for various codes}
\label{fig:prox:results_3d_multiple}
\end{figure}
\begin{figure}[H]
\centering
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
colormap/viridis,
xlabel={$\omega$}, ylabel={$\gamma$},
at={(0,0)}, view={0}{90},
zmode=log,
ytick={0, 0.05, 0.1, 0.15},
yticklabels={0, 0.05, 0.1, 0.15},
xtick={0.05, 0.1, 0.15, 0.2},
xticklabels={0.05, 0.1, 0.15, 0.2},
width=\textwidth,
height=0.75\textwidth,
point meta min=-5.7,
point meta max=-0.5,
]
\addplot3[
surf,
shader=flat,
mesh/rows=17, mesh/cols=10,
]
table [col sep=comma, x=omega, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_gamma_omega_963965.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=96, k=48$
\cite[\text{96.3.965}]{mackay_enc}}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
colormap/viridis,
xlabel={$\omega$}, ylabel={$\gamma$},
at={(0,0)}, view={0}{90},
zmode=log,
ytick={0, 0.05, 0.1, 0.15},
yticklabels={0, 0.05, 0.1, 0.15},
xtick={0.05, 0.1, 0.15, 0.2},
xticklabels={0.05, 0.1, 0.15, 0.2},
width=\textwidth,
height=0.75\textwidth,
point meta min=-5.7,
point meta max=-0.5,
]
\addplot3[
surf,
shader=flat,
mesh/rows=17, mesh/cols=10,
]
table [col sep=comma, x=omega, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_gamma_omega_bch_31_26.csv};
\end{axis}
\end{tikzpicture}
\caption{BCH code with $n=31, k=26$\\[2\baselineskip]}
\end{subfigure}%
\vspace{3mm}
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
colormap/viridis,
xlabel={$\omega$}, ylabel={$\gamma$},
at={(0,0)}, view={0}{90},
zmode=log,
ytick={0, 0.05, 0.1, 0.15},
yticklabels={0, 0.05, 0.1, 0.15},
xtick={0.05, 0.1, 0.15, 0.2},
xticklabels={0.05, 0.1, 0.15, 0.2},
width=\textwidth,
height=0.75\textwidth,
point meta min=-5.7,
point meta max=-0.5,
]
\addplot3[
surf,
shader=flat,
mesh/rows=17, mesh/cols=10,
]
table [col sep=comma, x=omega, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_gamma_omega_20433484.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=204, k=102$
\cite[\text{204.33.484}]{mackay_enc}}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
colormap/viridis,
xlabel={$\omega$}, ylabel={$\gamma$},
at={(0,0)}, view={0}{90},
zmode=log,
ytick={0, 0.05, 0.1, 0.15},
yticklabels={0, 0.05, 0.1, 0.15},
xtick={0.05, 0.1, 0.15, 0.2},
xticklabels={0.05, 0.1, 0.15, 0.2},
width=\textwidth,
height=0.75\textwidth,
point meta min=-5.7,
point meta max=-0.5,
]
\addplot3[
surf,
shader=flat,
mesh/rows=17, mesh/cols=10,
]
table [col sep=comma, x=omega, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_gamma_omega_20455187.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 5, 10 \right)$-regular \ac{LDPC} code with $n=204, k=102$
\cite[\text{204.55.187}]{mackay_enc}}
\end{subfigure}%
\vspace{3mm}
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
colormap/viridis,
xlabel={$\omega$}, ylabel={$\gamma$},
at={(0,0)}, view={0}{90},
zmode=log,
ytick={0, 0.05, 0.1, 0.15},
yticklabels={0, 0.05, 0.1, 0.15},
xtick={0.05, 0.1, 0.15, 0.2},
xticklabels={0.05, 0.1, 0.15, 0.2},
width=\textwidth,
height=0.75\textwidth,
point meta min=-5.7,
point meta max=-0.5,
]
\addplot3[
surf,
shader=flat,
mesh/rows=17, mesh/cols=10,
]
table [col sep=comma, x=omega, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_gamma_omega_40833844.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=408, k=204$
\cite[\text{408.33.844}]{mackay_enc}}
\end{subfigure}%
\hfill
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
colormap/viridis,
xlabel={$\omega$}, ylabel={$\gamma$},
at={(0,0)}, view={0}{90},
zmode=log,
ytick={0, 0.05, 0.1, 0.15},
yticklabels={0, 0.05, 0.1, 0.15},
xtick={0.05, 0.1, 0.15, 0.2},
xticklabels={0.05, 0.1, 0.15, 0.2},
width=\textwidth,
height=0.75\textwidth,
point meta min=-5.7,
point meta max=-0.5,
]
\addplot3[
surf,
shader=flat,
mesh/rows=17, mesh/cols=10,
]
table [col sep=comma, x=omega, y=gamma, z=BER]
{res/proximal/2d_ber_fer_dfr_gamma_omega_pegreg252x504.csv};
\end{axis}
\end{tikzpicture}
\caption{LDPC code (progressive edge growth construction) with $n=504, k=252$
\cite[\text{PEGReg252x504}]{mackay_enc}}
\end{subfigure}%
\vspace{5mm}
\begin{subfigure}{\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
hide axis,
scale only axis,
height=0pt,
width=0pt,
colormap/viridis,
colorbar horizontal,
point meta min=-5.7,
point meta max=-0.5,
colorbar style={
title={BER},
width=10cm,
xtick={-5,-4,...,-1},
xticklabels={$10^{-5}$,$10^{-4}$,$10^{-3}$,$10^{-2}$,$10^{-1}$}
}]
\addplot [draw=none] coordinates {(0,0)};
\end{axis}
\end{tikzpicture}
\end{subfigure}%
\caption{The \ac{BER} as a function of $\gamma$ and $\omega$ for various codes}
\label{fig:prox:gamma_omega_multiple}
\end{figure}
\begin{figure}[H]
\centering
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
legend columns=1,
legend pos=outer north east,
ymax=1.5, ymin=8e-5,
width=\textwidth,
height=0.75\textwidth,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_963965.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_963965.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_963965.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_963965.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_963965.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_963965.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=96, k=48$
\cite[\text{96.3.965}]{mackay_enc}}
\end{subfigure}%
\hfill%
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
legend columns=1,
legend pos=outer north east,
%legend columns=2,
%legend style={at={(0.5,-0.45)},anchor=south},
ymax=1.5, ymin=8e-5,
width=\textwidth,
height=0.75\textwidth,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_bch_31_26.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_bch_31_26.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_bch_31_26.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_bch_31_26.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_bch_31_26.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_bch_31_26.csv};
\end{axis}
\end{tikzpicture}
\caption{BCH code with $n=31, k=26$\\[\baselineskip]}
\end{subfigure}%
\vspace{3mm}
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
legend columns=1,
legend pos=outer north east,
xmin=0.5, xmax=6, xtick={1, ..., 5},
ymax=1.5, ymin=8e-5,
width=\textwidth,
height=0.75\textwidth,
]
\addplot[ForestGreen, mark=*, solid,]
table [x=SNR, y=FER, col sep=comma,
discard if not={gamma}{0.15},
discard if gt={SNR}{5.5},]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma,
discard if not={gamma}{0.15},
discard if gt={SNR}{5.5},]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=FER, col sep=comma,
discard if not={gamma}{0.01},
discard if gt={SNR}{5.5},]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma,
discard if not={gamma}{0.01},
discard if gt={SNR}{5.5},]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=FER, col sep=comma,
discard if not={gamma}{0.05},
discard if gt={SNR}{5.5},]
{res/proximal/2d_ber_fer_dfr_20433484.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma,
discard if not={gamma}{0.05},
discard if gt={SNR}{5.5},]
{res/hybrid/2d_ber_fer_dfr_20433484.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=204, k=102$
\cite[\text{204.33.484}]{mackay_enc}}
\end{subfigure}%
\hfill%
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
legend columns=1,
legend pos=outer north east,
%legend columns=2,
%legend style={at={(0.5,-0.45)},anchor=south},
ymax=1.5, ymin=8e-5,
width=\textwidth,
height=0.75\textwidth,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_20455187.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_20455187.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_20455187.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_20455187.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_20455187.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_20455187.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 5, 10 \right)$-regular \ac{LDPC} code with $n=204, k=102$
\cite[\text{204.55.187}]{mackay_enc}}
\end{subfigure}%
\vspace{3mm}
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
legend columns=1,
legend pos=outer north east,
%legend columns=2,
%legend style={at={(0.5,-0.45)},anchor=south},
ymax=1.5, ymin=8e-5,
width=\textwidth,
height=0.75\textwidth,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_40833844.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_40833844.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_40833844.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_40833844.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_40833844.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_40833844.csv};
\end{axis}
\end{tikzpicture}
\caption{$\left( 3, 6 \right)$-regular \ac{LDPC} code with $n=408, k=204$
\cite[\text{408.33.844}]{mackay_enc}}
\end{subfigure}%
\hfill%
\begin{subfigure}[t]{0.48\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[
grid=both,
xlabel={$E_b / N_0$ (dB)}, ylabel={FER},
ymode=log,
legend columns=1,
legend pos=outer north east,
ymax=1.5, ymin=8e-5,
width=\textwidth,
height=0.75\textwidth,
]
\addplot[ForestGreen, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/proximal/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot[Emerald, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.15}]
{res/hybrid/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot[NavyBlue, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/proximal/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot[RoyalPurple, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.01}]
{res/hybrid/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot[RedOrange, mark=*, solid]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/proximal/2d_ber_fer_dfr_pegreg252x504.csv};
\addplot[red, mark=triangle, densely dashed]
table [x=SNR, y=FER, col sep=comma, discard if not={gamma}{0.05}]
{res/hybrid/2d_ber_fer_dfr_pegreg252x504.csv};
\end{axis}
\end{tikzpicture}\\
\caption{\ac{LDPC} code (progressive edge growth construction) with $n=504, k=252$
\cite[\text{PEGReg252x504}]{mackay_enc}}
\label{fig:prox:improved:comp:504}
\end{subfigure}%
\vspace{5mm}
\begin{subfigure}[t]{\textwidth}
\centering
\begin{tikzpicture}
\begin{axis}[hide axis,
xmin=10, xmax=50,
ymin=0, ymax=0.4,
legend columns=3,
legend style={draw=white!15!black,legend cell align=left}]
\addlegendimage{ForestGreen, mark=*, solid}
\addlegendentry{proximal, $\gamma = 0.15$}
\addlegendimage{NavyBlue, mark=*, solid}
\addlegendentry{proximal, $\gamma = 0.01$}
\addlegendimage{RedOrange, mark=*, solid}
\addlegendentry{proximal, $\gamma = 0.05$}
\addlegendimage{Emerald, mark=triangle, densely dashed}
\addlegendentry{improved, $\gamma = 0.15$}
\addlegendimage{RoyalPurple, mark=triangle, densely dashed}
\addlegendentry{improved, $\gamma = 0.01$}
\addlegendimage{red, mark=triangle, densely dashed}
\addlegendentry{improved, $\gamma = 0.05$}
\end{axis}
\end{tikzpicture}
\end{subfigure}
\caption{Comparison of the decoding performance of proximal decoding
and the improved algorithm for various codes}
\label{fig:prox:improved:comp}
\end{figure}