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 2311.05052cs.ITmath.IT
收藏

从准等距嵌入到有限体积性质:量化矩阵补全的理论框架

From Quasi-Isometric Embeddings to Finite-Volume Property: A Theoretical Framework for Quantized Matrix Completion

University of Illinois Chicago(伊利诺伊大学芝加哥分校)

Arian Eamaz, Farhang Yeganegi, Mojtaba Soltanalian

AI总结:

本文提出了一种理论框架,研究无记忆标量量化对矩阵补全的影响,分析了掺杂方案、符号翻转和预量化噪声对恢复性能的影响,并提供了理论保证。

摘要:

我们深入探讨了无记忆标量量化对矩阵补全的影响。我们的主要动机是评估在不使用任何正则化项(如来自最大似然估计的项)的情况下,核范数最小化在处理量化矩阵问题中的恢复性能。我们将理论讨论扩展到包含掺杂方案的粗量化场景,其中低秩矩阵恢复可用的信息是几位低分辨率数据。我们为这两种情形提供理论保证:当在重建过程中可以访问掺杂物时,以及当仅能访问掺杂物的统计特性时。此外,我们全面分析了符号翻转和预量化噪声对恢复性能的影响,特别是在量化符号翻转影响时使用著名的汉明距离来度量恢复误差的上界。

英文摘要:

We delve into the impact of memoryless scalar quantization on matrix completion. Our primary motivation for this research is to evaluate the recovery performance of nuclear norm minimization in handling quantized matrix problems without the use of any regularization terms such as those stemming from maximum likelihood estimation. We broaden our theoretical discussion to encompass the coarse quantization scenario with a dithering scheme, where the only available information for low-rank matrix recovery is a few-bit low-resolution data. We furnish theoretical guarantees for both scenarios: when access to dithers is available during the reconstruction process, and when we have access solely to the statistical properties of the dithers. Additionally, we conduct a comprehensive analysis of the effects of sign flips and prequantization noise on the recovery performance, particularly when the impact of sign flips is quantified using the well-known Hamming distance in the upper bound of recovery error.

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。

↑