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 2302.11147math.OCstat.ML
收藏

信号处理与机器学习中超越梯度的随机近似

Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning

Aymeric Dieuleveut, Gersende Fort, Eric Moulines, Hoi-To Wai

AI总结:

本文提出基于Lyapunov函数的统一随机近似理论框架,涵盖非渐近与渐近收敛,并用于分析压缩随机梯度、随机EM和强化学习等非随机梯度算法。

摘要:

随机近似(Stochastic Approximation,SA)是一种经典算法,自早期以来便对信号处理产生了巨大影响;如今,由于需要处理大量在不确定性下观测到的数据,它也对机器学习产生了巨大影响。SA的一个典型特例涉及广受欢迎的随机(次)梯度算法,后者是许多重要应用背后的主力工具。一个较少为人所知的事实是,SA方案还可扩展到非随机梯度算法,例如压缩随机梯度、随机期望最大化以及许多强化学习算法。本文旨在通过给出一套有理论支撑的SA算法设计指南,向信号处理和机器学习领域的读者概述并介绍SA的非随机梯度视角。我们的中心主题是提出一个通用框架,统一SA的现有理论,包括其非渐近和渐近收敛结果,并展示这些理论在流行的非随机梯度算法上的应用。我们基于满足多种温和条件的Lyapunov函数类别构建分析框架。我们在非随机梯度算法与Lyapunov函数为光滑、凸或强凸的情形之间建立联系。利用上述框架,我们通过具体示例说明非随机梯度算法的收敛性质。本文还将讨论对新兴方差缩减技术的扩展,以改善样本复杂度。

英文摘要:

Stochastic Approximation (SA) is a classical algorithm that has had since the early days a huge impact on signal processing, and nowadays on machine learning, due to the necessity to deal with a large amount of data observed with uncertainties. An exemplar special case of SA pertains to the popular stochastic (sub)gradient algorithm which is the working horse behind many important applications. A lesser-known fact is that the SA scheme also extends to non-stochastic-gradient algorithms such as compressed stochastic gradient, stochastic expectation-maximization, and a number of reinforcement learning algorithms. The aim of this article is to overview and introduce the non-stochastic-gradient perspectives of SA to the signal processing and machine learning audiences through presenting a design guideline of SA algorithms backed by theories. Our central theme is to propose a general framework that unifies existing theories of SA, including its non-asymptotic and asymptotic convergence results, and demonstrate their applications on popular non-stochastic-gradient algorithms. We build our analysis framework based on classes of Lyapunov functions that satisfy a variety of mild conditions. We draw connections between non-stochastic-gradient algorithms and scenarios when the Lyapunov function is smooth, convex, or strongly convex. Using the said framework, we illustrate the convergence properties of the non-stochastic-gradient algorithms using concrete examples. Extensions to the emerging variance reduction techniques for improved sample complexity will also be discussed.

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。

↑