arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.11235math.OC
收藏

《(随机)梯度方法收敛定理手册》

Handbook of Convergence Theorems for (Stochastic) Gradient Methods

Guillaume Garrigos, Robert M. Gower

AI总结:

本手册收录梯度及随机梯度下降类方法在多种函数条件下的简洁优质收敛证明,覆盖确定性、随机变体及非光滑问题相关方法,聚焦全局收敛与复杂度速率,含部分少见证明且各章可独立查阅。

摘要:

这是一本收录梯度及随机梯度下降类方法收敛性简洁证明的手册。我们研究的函数包括Lipschitz函数、光滑函数、凸函数、强凸函数和/或Polyak-Łojasiewicz函数。我们的重点是兼具简洁性的“优质证明”,每个章节均可独立查阅。我们从梯度下降的证明入手,接着介绍含小批量处理、动量在内的随机变体,随后延伸至非光滑问题,涵盖次梯度法、近端梯度下降及其随机变体。研究聚焦于全局收敛速率与复杂度速率,书中还包含一些稍少见的证明,如带近端步的SGD(随机梯度下降)、带动量的SGD以及无放回小批量SGD的证明。

英文摘要:

This is a handbook of simple proofs of the convergence of gradient and stochastic gradient descent type methods. We consider functions that are Lipschitz, smooth, convex, strongly convex, and/or Polyak-Łojasiewicz functions. Our focus is on ``good proofs'' that are also simple. Each section can be consulted separately. We start with proofs of gradient descent, then on stochastic variants, including minibatching and momentum. Then move on to nonsmooth problems with the subgradient method, the proximal gradient descent and their stochastic variants. Our focus is on global convergence rates and complexity rates. Some slightly less common proofs found here include that of SGD (Stochastic gradient descent) with a proximal step, with momentum, and with mini-batching without replacement.

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。

↑