Overview

Minimax regret asks how well a decision-maker can perform, in the worst case, compared with a benchmark that knew the outcomes or model in advance. It studies settings from bandits and reinforcement learning to online prediction, pricing, and resource allocation, using methods such as UCB, elimination, mirror descent, and robust optimization. Researchers pair algorithmic regret guarantees with information-theoretic lower bounds to determine which rates are achievable. A central tension is that feedback, dimension, heavy-tailed noise, and constraints such as fairness or safety can sharply change those rates, while algorithms must often adapt without knowing which conditions apply.

Latest papers

CardsList

69 papers16 papers in the last four weeks, down 6% on the four weeks before. 0.1% of all new papers.

  1. Water-Filling is Universally Minimax Optimal

    Mar 27, 2026Siddhartha Banerjee, Ramiro N. Deo-Campo Vuong, Robert KleinbergOnline Resource AllocationMulti-Agent Resource Allocation

  2. Globalized Adversarial Regret Optimization: Robust Decisions with Uncalibrated Predictions

    Mar 26, 2026Jannis Kurtz, Bart P. G. van ParysRobust OptimizationPredict-Then-Optimize

  3. Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs

    Mar 25, 2026Guy Zamir, Matthew Zurek, Yudong ChenRegret Minimization in RLAverage-Reward RL

  4. Few Batches or Little Memory, But Not Both: Simultaneous Space and Adaptivity Constraints in Stochastic Bandits

    Mar 14, 2026Ruiyuan Huang, Zicheng Lyu, Xiaoyi Zhu +1Batched BanditsMulti-Armed Bandits

  5. Learning Optimal Search Strategies

    Mar 2, 2026Stefan Ankirchner, Maximilian Philipp ThielOptimal StoppingMinimax Regret

  6. What is the Value of Censored Data? An Exact Analysis for the Data-driven Newsvendor

    Feb 18, 2026Rachitesh Kumar, Omar MouchtakiInventory ControlMinimax Regret

  7. Linear Bandits on Ellipsoids: Minimax Optimal Algorithms

    Feb 24, 2025Raymond Zhang, Hedi Hadiji, Richard CombesMulti-Armed BanditsMinimax Regret