arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.04481cs.ITmath.IT
收藏

极小极大率失真

Minimax Rate-Distortion

Adeel Mahmood, Aaron B. Wagner

摘要:

我们证明了存在的可变速率率失真码,满足失真约束几乎肯定和极大极小,即,相对于未知源分布和仅在运行时向编码器揭示的失真度量,该失真度量是强通用的。如果我们只需要极小极大的普遍性相对于源分布,而不是失真的措施,那么我们提供了一个可实现的$\tilde{O}(1/\sqrt{n})$冗余率,我们表明是最佳的。这是在对比通用有损压缩,它提供了$O(\log n/n)$冗余保证弱通用代码在各种规则性条件下的现有工作。我们发现,无论是消除的规则性条件或升级到强的普遍性,同时保持这些规则性条件,必然会增加冗余$\tilde{O}(1/\sqrt{n})$。我们的构造涉及非独立同分布的随机编码。码字和零速率未编码传输方案。证明使用大偏差的精确渐近性、接受-拒绝抽样和失真度量的VC维。

英文摘要:

We show the existence of variable-rate rate-distortion codes that meet the disortion constraint almost surely and are minimax, i.e., strongly, universal with respect to an unknown source distribution and a distortion measure that is revealed only to the encoder and only at runtime. If we only require minimax universality with respect to the source distribution and not the distortion measure, then we provide an achievable $\tilde{O}(1/\sqrt{n})$ redundancy rate, which we show is optimal. This is in contrast to prior work on universal lossy compression, which provides $O(\log n/n)$ redundancy guarantees for weakly universal codes under various regularity conditions. We show that either eliminating the regularity conditions or upgrading to strong universality while keeping these regularity conditions entails an inevitable increase in the redundancy to $\tilde{O}(1/\sqrt{n})$. Our construction involves random coding with non-i.i.d.\ codewords and a zero-rate uncoded transmission scheme. The proof uses exact asymptotics from large deviations, acceptance-rejection sampling, and the VC dimension of distortion measures.

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。

↑