Prediction with Expert Advice: Anytime Regret with Many Experts Matches the Fixed-Time Constant

arXiv:2609.27206 · stat.ML, cs.LG · Submitted 2026-09-23 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-09-23

Updated: 2026-09-23

Terminology

• Regret — 52× in this paper · explained in 3 episodes
• Conference on Learning Theory — 4× in this paper
• International Conference on Machine Learning — 3× in this paper
• International Conference on Algorithmic Learning Theory — 2× in this paper
• Adaptation — 1× in this paper · explained in 1 episode
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 13 episodes
• Minimax Regret — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB
• Experimental Evidence for Asymptotic Non-Optimality of Comb Adversary Strategy
• On Theorem 2.3 in "Prediction, Learning, and Games" by Cesa-Bianchi and Lugosi
• A second order regret bound for NormalHedge
• Optimal Non-Asymptotic Lower Bound on the Minimax Regret of Learning with Expert Advice

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey