Optimal Alternating Regret for Online Learning and Games

arXiv:2608.24731 · cs.LG, cs.GT, stat.ML · Submitted 2026-08-25 · Read on arXiv

cs.LG, cs.GT, stat.ML

Submitted: 2026-08-25

Updated: 2026-08-25

Terminology

• Regret — 105× in this paper · explained in 3 episodes
• Alternation — 16× in this paper · explained in 1 episode
• Loss Function — 8× in this paper · explained in 2 episodes
• Nash Equilibrium — 3× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Online Learning: A Modern Introduction Using Convex Optimization
• Negative Stepsizes Make Gradient-Descent-Ascent Converge
• Solving Large Imperfect Information Games Using CFR+
• Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks