arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.13554cs.ITmath.IT
收藏

用于信源编码的神经极化码

Neural Polar Codes for Source Coding

Ben-Gurion University(本-古里安大学);Duke University(杜克大学)

Bashar Huleihel, Ziv Aharoni, Haim H. Permuter

AI总结:

本文提出神经极化译码器,无需显式信源模型即可实现无损、有损及Wyner-Ziv信源压缩,实验表明其性能接近解析SC译码器,且适用于传统方法不可行的场景。

摘要:

本文提出一种基于数据驱动的方法,用于使用极化码实现无损和有损信源压缩。经典极化信源编码对于二元无记忆信源可在低复杂度下达到基本极限,但对于具有记忆的未知q元信源,连续消除(SC)译码需要显式信源模型,且计算成本高昂。本文推导了解析SC递归关系,证明精确实现的复杂度随字母表大小呈二次增长,随状态空间大小呈三次增长。为克服这些限制,本文开发了神经极化译码器,直接从数据中训练以近似合成极化坐标的条件分布,无需显式信源模型。这些学习到的分布可用于估计熵率、互信息和率失真函数,并支持显式极化压缩方案。对于无损压缩,本文识别高熵极化坐标,并使用学习到的SC递归重构剩余坐标;对于有损压缩,本文将神经极化译码器与神经测试信道结合,以估计和优化互信息-失真权衡,并构建显式有损极化码。本文还将该框架扩展到具有译码器侧信息的Wyner-Ziv压缩,方法是学习条件极化分布和重构映射。在无记忆信源、带记忆信源和真实基因组数据上的实验表明,当解析SC译码器可用时,学习到的译码器与其性能接近;当传统方法计算不可行或信源模型不可用时,学习到的译码器仍适用。

英文摘要:

This paper presents a data-driven approach to lossless and lossy source compression using polar codes. Classical polar source coding achieves fundamental limits with low complexity for binary memoryless sources. However, for unknown q-ary sources with memory, successive-cancellation (SC) decoding requires an explicit source model and can be computationally prohibitive. We present analytical SC recursions and show that exact implementations scale quadratically with alphabet size and cubically with state-space size. To overcome these limitations, we develop neural polar decoders trained directly from data to approximate conditional distributions of synthetic polar coordinates without requiring an explicit source model. These learned distributions enable estimation of entropy rates, mutual information, and rate-distortion functions, and support explicit polar compression schemes. For lossless compression, we identify high-entropy polarized coordinates and reconstruct the remaining coordinates using the learned SC recursion. For lossy compression, we combine neural polar decoders with a neural test channel to estimate and optimize the mutual information-distortion tradeoff and construct an explicit lossy polar code. We also extend the framework to Wyner-Ziv compression with decoder side information by learning conditional polarized distributions and a reconstruction mapping. Experiments on memoryless sources, sources with memory, and real genomic data show that the learned decoders closely match analytical SC decoders when available and remain applicable when conventional methods are computationally infeasible or the source model is unavailable.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑