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

被引:1
作者
Sorin, Sylvain [1 ]
机构
[1] Sorbonne Univ, Inst Math Jussieu, CNRS UMR 7586, PRG, Campus Pierre Marie Curie, Paris, France
关键词
68T05; 68W27; 68W50; 90C25; 91A26; PROJECTED SUBGRADIENT METHODS; DYNAMICAL-SYSTEMS; 1ST-ORDER METHODS; VARIATIONAL-INEQUALITIES; MONOTONE-OPERATORS; GRADIENT; CONVERGENCE; DESCENT; APPROXIMATIONS; MINIMIZATION;
D O I
10.1007/s10107-023-01927-7
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
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.
引用
收藏
页码:645 / 686
页数:42
相关论文
共 107 条
[61]   The projection dynamic and the geometry of population games [J].
Lahkar, Ratul ;
Sandholm, William H. .
GAMES AND ECONOMIC BEHAVIOR, 2008, 64 (02) :565-590
[62]   A wide range no-regret theorem [J].
Lehrer, E .
GAMES AND ECONOMIC BEHAVIOR, 2003, 42 (01) :101-115
[63]  
Lehrer E, 2007, J CONVEX ANAL, V14, P271
[64]  
Levitin E. S., 1966, USSR Computational Mathematics and Mathematical Physics, V6, P1, DOI DOI 10.1016/0041-5553(66)90114-5
[65]   THE WEIGHTED MAJORITY ALGORITHM [J].
LITTLESTONE, N ;
WARMUTH, MK .
INFORMATION AND COMPUTATION, 1994, 108 (02) :212-261
[66]   RELATIVELY SMOOTH CONVEX OPTIMIZATION BY FIRST-ORDER METHODS, AND APPLICATIONS [J].
Lu, Haihao ;
Freund, Robert M. ;
Nesterov, Yurii .
SIAM JOURNAL ON OPTIMIZATION, 2018, 28 (01) :333-354
[67]   Learning in games with continuous action sets and unknown payoff functions [J].
Mertikopoulos, Panayotis ;
Zhou, Zhengyuan .
MATHEMATICAL PROGRAMMING, 2019, 173 (1-2) :465-507
[68]   Riemannian game dynamics [J].
Mertikopoulos, Panayotis ;
Sandholm, William H. .
JOURNAL OF ECONOMIC THEORY, 2018, 177 :315-364
[69]   Learning in Games via Reinforcement and Regularization [J].
Mertikopoulos, Panayotis ;
Sandholm, William H. .
MATHEMATICS OF OPERATIONS RESEARCH, 2016, 41 (04) :1297-1324