arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.07941cs.ITcs.DCcs.LGmath.IT
收藏

高失真区单位范数向量的最优压缩

Optimal Compression of Unit Norm Vectors in the High Distortion Regime

University of California, San Diego(加利福尼亚大学圣迭戈分校);Indian Institute of Technology, Bombay(印度理工学院孟买分校)

Heng Zhu, Avishek Ghosh, Arya Mazumdar

AI总结:

针对分布式学习中单位范数向量的高效压缩,本文在高失真最坏情形下,允许随机化映射,确定了有偏与无偏压缩的最优率,并证明简单方案近乎最优。

摘要:

受通信高效分布式学习需求的驱动,我们研究了将单位范数向量压缩为最少比特数的方法,同时允许在恢复时存在一定可接受的失真水平。这一问题在率失真/覆盖码文献中已有探讨,但我们的关注点完全限定在“高失真”区域。我们在最坏情形下处理该问题,不利用向量的任何先验信息,但允许使用随机化压缩映射。我们的研究同时考虑有偏和无偏压缩方法,并确定了最优压缩率。结果表明,简单压缩方案在该情形下近乎最优。虽然结果包含新结果与已知结果,但为完整性起见,本文将其汇编在一起。

英文摘要:

Motivated by the need for communication-efficient distributed learning, we investigate the method for compressing a unit norm vector into the minimum number of bits, while still allowing for some acceptable level of distortion in recovery. This problem has been explored in the rate-distortion/covering code literature, but our focus is exclusively on the "high-distortion" regime. We approach this problem in a worst-case scenario, without any prior information on the vector, but allowing for the use of randomized compression maps. Our study considers both biased and unbiased compression methods and determines the optimal compression rates. It turns out that simple compression schemes are nearly optimal in this scenario. While the results are a mix of new and known, they are compiled in this paper for completeness.

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。

↑