View PDF HTML (experimental)

Abstract:Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a $\delta$-explicit minimax-quantile theory for interactive statistical decision making (ISDM). We first provide structural relations between minimax quantiles, lower minimax quantiles, and minimax risk. This includes a quantile-to-expectation conversion and an equivalence between strict and lower minimax quantiles outside a countable set of confidence levels. We then derive two converse tools for ISDM: a high-probability interactive Fano's method and a high-probability interactive Le Cam's method. Then, we show that mutual-information (MI) privacy can be handled in the same framework by restricting the admissible decision class. For coordinatewise Gaussian privatization, we derive a two-point template that isolates the privacy-induced variance inflation. We instantiate this template for Gaussian mean estimation, and use the same two-point strategy directly for two-armed Gaussian bandits. We then derive a minimax quantile lower bound for the $K$-armed Gaussian bandit problem, showing that the interactive Fano method captures the exploration cost over multiple possible best arms. The resulting lower bounds are explicit in the confidence level $\delta$ and in the privacy budget for the private problems. They yield $\log(1/\delta)/n$ scaling for squared-error Gaussian mean estimation, $\sqrt{T\log(1/\delta)}$ scaling for two-armed bounded-mean Gaussian bandits, and $\sqrt{KT\log(1/\delta)}$-type scaling for the $K$-armed bandits, with privacy appearing through a Gaussian variance-inflation factor for the private problems.

Submission history

From: Raghav Bongole [view email]
[v1] Mon, 22 Jun 2026 09:41:48 UTC (106 KB)