Learning Maximum Margin Channel Decoders

Tsvieli, Amit; Weinberger, Nir

doi:10.1109/tit.2023.3243869

Cited by 3 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some exemplary (relatively) recent applications of (squared) Mahalanobis distance can be found e.g. in Xu et al [301], Sun et al [302], Timmermann et al [303], Wauchope et al [304], Weinberger [305], Wen et al [306], Yang et al [307], Zhang et al [308], Burssens et al [309], Choi et al [310], Choi et al [311], Dahlin et al [312], Ebrahimi et al [313], Jeong et al [314], Kim et al [315], Nowakowski et al [316], Qu et al [317], Rabby et al [318], Sarno et al [319], Tang et al [320], Tsvieli & Weinberger [321], Zhang et al [322], Zhou et al [323]. Some exemplary (relatively) recent applications of generally non-separable (ordinary/classical) Bregman distances appear e.g.…”

Section: A Further Divergences and Friendsmentioning

confidence: 99%

A Precise Bare Simulation Approach to the Minimization of Some Distances. I. Foundations

Broniatowski¹,

Stummer

2023

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

The constrained minimization (respectively maximization) of directed distances and of related generalized entropies is a fundamental task in information theory as well as in the adjacent fields of statistics, machine learning, artificial intelligence, signal processing and pattern recognition. In our previous paper "A precise bare simulation approach to the minimization of some distances. I. Foundations", we obtained such kind of constrained optima by a new dimension-free precise bare (pure) simulation method, provided basically that (i) the underlying directed distance is of f −divergence type, and that (ii) this can be connected to a light-tailed probability distribution in a certain manner. In the present paper, we extend this approach such that constrained optimization problems of a very huge amount of directed distances and generalized entropies -and beyond -can be tackled by a newly developed dimension-free extended bare simulation method, for obtaining both optima as well as optimizers. Almost no assumptions (like convexity) on the set of constraints are needed, within our discrete setup of arbitrary dimension, and our method is precise (i.e., converges in the limit). For instance, we cover constrained optimizations of arbitrary f −divergences, Bregman distances, scaled Bregman distances and weighted ℓr−distances. The potential for wide-spread applicability is indicated, too; in particular, we deliver many recent references for uses of the involved distances/divergences in various different research fields (which may also serve as an interdisciplinary interface).

show abstract

Section: A Further Divergences and Friendsmentioning

confidence: 99%

A Precise Bare Simulation Approach to the Minimization of Some Distances. I. Foundations

Broniatowski¹,

Stummer

2023

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

show abstract

“…Kurmukova et al [239] Friendly jamming for improving decoding performance. Tsvieli et al [240] Investigation on the problem of maximizing the margin of the decoder. Zhong et al [241], [242] DL-based decoders for spin-torque transfer magnetic random access memory.…”

Section: Other Approachesmentioning

confidence: 99%

“…the generalization properties, remains challenging. The authors in [240] addressed the problem of maximizing the margin of the decoder for an additive noise channel whose noise distribution is unknown, as well as for a nonlinear channel with AWGN. They formulated a maximum margin optimization problem, which is common in support vector machines (SVMs), for the decoder learning problem, and they relaxed it to a regularized loss minimization (RLM) problem by several approximation steps.…”

Section: Other Approachesmentioning

confidence: 99%

Security Gap Improvement of BICM Systems Through Bit-Labeling Optimization for the Gaussian Wiretap Channel

2022

View full text Add to dashboard Cite

This paper provides a comprehensive survey on recent advances in deep learning (DL) techniques for the channel coding problems. Inspired by the recent successes of DL in a variety of research domains, its applications to the physical layer technologies have been extensively studied in recent years, and are expected to be a potential breakthrough in supporting the emerging use cases of the next generation wireless communication systems such as 6G. In this paper, we focus exclusively on the channel coding problems and review existing approaches that incorporate advanced DL techniques into code design and channel decoding. After briefly introducing the background of recent DL techniques, we categorize and summarize a variety of approaches, including model-free and mode-based DL, for the design and decoding of modern error-correcting codes, such as low-density parity check (LDPC) codes and polar codes, to highlight their potential advantages and challenges. Finally, the paper concludes with a discussion of open issues and future research directions in channel coding.

show abstract