English

Risk level dependent Minimax Quantile lower bounds for Interactive Statistical Decision Making

Information Theory 2025-10-08 v1 Artificial Intelligence math.IT

Abstract

Minimax risk and regret focus on expectation, missing rare failures critical in safety-critical bandits and reinforcement learning. Minimax quantiles capture these tails. Three strands of prior work motivate this study: minimax-quantile bounds restricted to non-interactive estimation; unified interactive analyses that focus on expected risk rather than risk level specific quantile bounds; and high-probability bandit bounds that still lack a quantile-specific toolkit for general interactive protocols. To close this gap, within the interactive statistical decision making framework, we develop high-probability Fano and Le Cam tools and derive risk level explicit minimax-quantile bounds, including a quantile-to-expectation conversion and a tight link between strict and lower minimax quantiles. Instantiating these results for the two-armed Gaussian bandit immediately recovers optimal-rate bounds.

Keywords

Cite

@article{arxiv.2510.05808,
  title  = {Risk level dependent Minimax Quantile lower bounds for Interactive Statistical Decision Making},
  author = {Raghav Bongole and Amirreza Zamani and Tobias J. Oechtering and Mikael Skoglund},
  journal= {arXiv preprint arXiv:2510.05808},
  year   = {2025}
}
R2 v1 2026-07-01T06:21:07.078Z