arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08669cs.ITmath.IT
收藏

通过单次噪声整形实现带限图数据的可靠一比特量化

Reliable one-bit quantization of bandlimited graph data via single-shot noise shaping

Ludwig-Maximilians-Universität(路德维希-马克西米利安大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Technical University of Munich(慕尼黑工业大学);Munich Data Science Institute(慕尼黑数据科学研究所)

Johannes Maly, Anna Veselovska

AI总结:

本文提出一种高效单次噪声整形方法,在低通滤波下实现图结构带限数据的低比特率量化,具有最先进的性能和严格误差界。

摘要:

图数据在自然科学和机器学习中普遍存在。本文考虑在低通滤波下对图结构带限数据进行低比特率量化以保留信息的问题。我们提出了一种高效的单次噪声整形方法,实现了最先进的性能,并具有严格的误差界。与现有方法不同,该方法允许可靠地对任意比特级进行量化,包括每个数据系数使用单比特的极端情况。

英文摘要:

Graph data are ubiquitous in natural sciences and machine learning. In this paper, we consider the problem of quantizing graph structured, bandlimited data to few bits per entry while preserving its information under low-pass filtering. We propose an efficient single-shot noise shaping method that achieves state-of-the-art performance and comes with rigorous error bounds. In contrast to existing methods it allows reliable quantization to arbitrary bit-levels including the extreme case of using a single bit per data coefficient.

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。

↑