Content tagged with 2026

• Publications menu and navigation
• [B1] Regret, equilibrium, and learning in games: A guided tour
• [W8] Constant regret in general games via higher-order optimism
• [J49] Explicit second-order min-max optimization: Practical algorithms and complexity analysis
• [C110] State-action selection in general stochastic games under regularized policy gradient methods
• [C109] The long-run distribution of regularized learning in games: A large deviations approach
• [C108] Adapting to conflict: Equilibrium structure and adaptive learning in harmonic games
• [C107] The computational intractability of not worst-responding
• [C106] Leveraging similarities in multi-armed bandits
• [C105] What preferences can–and cannot–predict in multi-agent online learning
• [C104] Taming stochastic gradient descent: Almost sure convergence and saddle-point avoidance under (L0,L1)-smoothness
• [C103] Bregman meets Lévy: Stochastic mirror descent with heavy-tailed noise in continuous and discrete time
• [C102] Efficient swap regret minimization in combinatorial bandits