No-regret algorithms in on-line learning, games and convex optimization

• 成果类型: Article
• 署名作者: Sorin, Sylvain
• 署名单位: Sorbonne Universite; Centre National de la Recherche Scientifique (CNRS); CNRS - National Institute for Mathematical Sciences (INSMI); Universite Paris Cite
• 刊物名称: MATHEMATICAL PROGRAMMING
• ISSN/ISSBN: 0025-5610
• DOI: 10.1007/s10107-023-01927-7
• 发表日期: 2024
• 页码: 645-686
• 关键词: projected subgradient methods; DYNAMICAL-SYSTEMS; 1st-order methods; variational-inequalities; monotone-operators; gradient; CONVERGENCE; descent; approximations; minimization

摘要

The purpose of this article is to underline the links between some no-regret algorithms used in on-line learning, games and convex optimization and to compare the continuous and discrete time versions.