Convex-Concave Min-Max Stackelberg Games

被引:0
|
作者
Goktas, Denizalp [1 ]
Greenwald, Amy [1 ]
机构
[1] Brown Univ, Dept Comp Sci, Providence, RI 02912 USA
关键词
VARIATIONAL-INEQUALITIES; EQUILIBRIUM; OPTIMIZATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Min-max optimization problems (i.e., min-max games) have been attracting a great deal of attention because of their applicability to a wide range of machine learning problems. Although significant progress has been made recently, the literature to date has focused on games with independent strategy sets; little is known about solving games with dependent strategy sets, which can be characterized as min-max Stackelberg games. We introduce two first-order methods that solve a large class of convex-concave min-max Stackelberg games, and show that our methods converge in polynomial time. Min-max Stackelberg games were first studied by Wald, under the posthumous name of Wald's maximin model, a variant of which is the main paradigm used in robust optimization, which means that our methods can likewise solve many convex robust optimization problems. We observe that the computation of competitive equilibria in Fisher markets also comprises a min-max Stackelberg game. Further, we demonstrate the efficacy and efficiency of our algorithms in practice by computing competitive equilibria in Fisher markets with varying utility structures. Our experiments suggest potential ways to extend our theoretical results, by demonstrating how different smoothness properties can affect the convergence rate of our algorithms.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] On the Initialization for Convex-Concave Min-max Problems
    Liu, Mingrui
    Orabona, Francesco
    [J]. INTERNATIONAL CONFERENCE ON ALGORITHMIC LEARNING THEORY, VOL 167, 2022, 167
  • [2] A delayed subgradient method for nonsmooth convex-concave min-max optimization problems
    Arunrat, Tipsuda
    Nimana, Nimit
    [J]. RESULTS IN CONTROL AND OPTIMIZATION, 2023, 12
  • [3] HIGHER-ORDER METHODS FOR CONVEX-CONCAVE MIN-MAX OPTIMIZATION AND MONOTONE VARIATIONAL INEQUALITIES
    Bullins, Brian
    Lai, Kevin A.
    [J]. SIAM JOURNAL ON OPTIMIZATION, 2022, 32 (03) : 2208 - 2229
  • [4] Convex-Concave 0-Sum Markov Stackelberg Games
    Goktas, Denizalp
    Prakash, Arjun
    Greenwald, Amy
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [5] Last Iterate Convergence in No-regret Learning: Constrained Min-max Optimization for Convex-concave Landscapes
    Lei, Qi
    Nagarajan, Sai Ganesh
    Panageas, Ioannis
    Wang, Xiao
    [J]. 24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
  • [6] Distributed Solutions of Convex-Concave Games on Networks
    Xiao, Yingying
    Hou, Xiaodong
    Hu, Jianghai
    [J]. 2019 AMERICAN CONTROL CONFERENCE (ACC), 2019, : 1189 - 1194
  • [7] FINDING NORMALIZED EQUILIBRIUM IN CONVEX-CONCAVE GAMES
    Flam, S. D.
    Ruszczynski, A.
    [J]. INTERNATIONAL GAME THEORY REVIEW, 2008, 10 (01) : 37 - 51
  • [8] Weakly-convex-concave min-max optimization: provable algorithms and applications in machine learning
    Rafique, Hassan
    Liu, Mingrui
    Lin, Qihang
    Yang, Tianbao
    [J]. OPTIMIZATION METHODS & SOFTWARE, 2022, 37 (03): : 1087 - 1121
  • [9] DIFFERENTIAL DELAYED GAMES, THEOREM OF MIN-MAX
    BLAQUIERE, A
    CAUSSIN, P
    [J]. COMPTES RENDUS HEBDOMADAIRES DES SEANCES DE L ACADEMIE DES SCIENCES SERIE A, 1971, 273 (23): : 1178 - +
  • [10] Semidefinite programming for min-max problems and games
    Laraki, R.
    Lasserre, J. B.
    [J]. MATHEMATICAL PROGRAMMING, 2012, 131 (1-2) : 305 - 332