arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.03401math.OC
收藏

重新审视随机近点法:通用光滑性和相似性

Revisiting Stochastic Proximal Point Methods: Generalized Smoothness and Similarity

King Abdullah University of Science and Technology(阿卜杜拉国王科技大学)

Zhirayr Tovmasyan, Grigory Malinovsky, Laurent Condat, Peter Richtárik

AI总结:

本文提出了一种新的phi-光滑性框架,对随机近点法进行了全面分析,并通过实验验证了其在非光滑优化中的应用扩展。

摘要:

非光滑优化问题在机器学习中的日益普及,推动了对通用光滑性假设的研究。其中,(L0, L1)-光滑性假设已成为最突出的假设之一。尽管近点方法在确定性设置中适用于非光滑问题,其随机版本仍被低估。本文聚焦于随机近点法(SPPM),因其稳定性及最小超参数调优的优势,常在随机梯度下降(SGD)中缺失。我们提出了一种新的phi-光滑性框架,并在不依赖传统光滑性假设的情况下对SPPM进行了全面分析。我们的结果非常通用,涵盖了现有发现作为特殊情况。此外,我们研究了SPPM在广泛采用的期望相似性假设下的应用,从而将其适用范围扩展到更广泛的情境。我们的理论贡献通过实际实验进行了说明和验证。

英文摘要:

The growing prevalence of nonsmooth optimization problems in machine learning has spurred significant interest in generalized smoothness assumptions. Among these, the (L0, L1)-smoothness assumption has emerged as one of the most prominent. While proximal methods are well-suited and effective for nonsmooth problems in deterministic settings, their stochastic counterparts remain underexplored. This work focuses on the stochastic proximal point method (SPPM), valued for its stability and minimal hyperparameter tuning-advantages often missing in stochastic gradient descent (SGD). We propose a novel phi-smoothness framework and provide a comprehensive analysis of SPPM without relying on traditional smoothness assumptions. Our results are highly general, encompassing existing findings as special cases. Furthermore, we examine SPPM under the widely adopted expected similarity assumption, thereby extending its applicability to a broader range of scenarios. Our theoretical contributions are illustrated and validated by practical experiments.

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。

↑