arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.09545math.OCcs.LGcs.NAmath.NA
收藏

加速方法

Acceleration Methods

CNRS(法国国家科学研究中心);Ecole Normale Supérieure(巴黎高等师范学院);Samsung SAIT AI Lab(三星SAIT人工智能实验室);Mila(米拉实验室);INRIA(法国国家信息与自动化研究所)

Alexandre d'Aspremont, Damien Scieur, Adrien Taylor

AI总结:

本专著介绍了凸优化中动量法、嵌套优化、近端加速及重启方案等加速技术的最新进展,通过主模板构建收敛性证明,并解决对未知正则性参数的适应问题。

摘要:

本专著涵盖了凸优化中常用的一系列加速技术的最新进展。我们首先利用二次优化问题引入两大类关键方法,即动量法和嵌套优化方案。它们在二次问题中重合,形成 Chebyshev 方法。我们详细讨论动量方法,从 Nesterov 的开创性工作出发,并使用几个主模板来构建收敛性证明,例如优化梯度方法的模板,其主要优势在于展示动量方法如何优化收敛保证。我们进一步探讨近端加速,它是 Catalyst 和 Accelerated Hybrid Proximal Extragradient 框架的核心,采用类似的算法模式。常见的加速技术直接依赖于对当前问题某些正则性参数的了解。最后,我们讨论重启方案,这是一组简单的技术,能够在适应未观测正则性参数的同时,达到近乎最优的收敛速率。

英文摘要:

This monograph covers some recent advances in a range of acceleration techniques frequently used in convex optimization. We first use quadratic optimization problems to introduce two key families of methods, namely momentum and nested optimization schemes. They coincide in the quadratic case to form the Chebyshev method. We discuss momentum methods in detail, starting with the seminal work of Nesterov and structure convergence proofs using a few master templates, such as that for optimized gradient methods, which provide the key benefit of showing how momentum methods optimize convergence guarantees. We further cover proximal acceleration, at the heart of the Catalyst and Accelerated Hybrid Proximal Extragradient frameworks, using similar algorithmic patterns. Common acceleration techniques rely directly on the knowledge of some of the regularity parameters in the problem at hand. We conclude by discussing restart schemes, a set of simple techniques for reaching nearly optimal convergence rates while adapting to unobserved regularity parameters.

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。

↑