Logarithmic Regret for Alternating Mirror Descent
cs.LG, cs.GT, math.OC, stat.ML
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/CoffeeAndConvexity/AltOMD-Lean
Terminology
Sources
- Constant regret in general games via higher-order optimism
- A variation of Eichler's proof of the Baker-Campbell-Hausdorff formula
- Constant Individual Regret in General Games
- Multiplicative Optimism for Constant Regret in Games
- IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence
- Optimal Alternating Regret for Online Learning and Games
- Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization
- Minimax Alternating Regret for the Experts Problem and Online Convex Optimization
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis