Paper: Minimax Quantile Bounds via Information Measures
chaumian · x · 2026-08-24
This paper develops a unified information-theoretic framework for lower bounding minimax quantiles. Starting from a loss-adapted Neyman-Pearson metaconverse, it bounds the minimax success probability by separating the small-ball geometry from statistical distinguishability. Different relaxations yield converses based on various information measures. The framework is used to derive finite-sample bounds for the Gaussian weighted stochastic block model and low-rank matrix estimation.
More from Research
- 10 Claude Opus 5.5 agents prove faster shortest-path algorithm in Lean within 15 hours — ricklamers · 2026-09-23
- ImIR replaces text prompts with image instructions for all-in-one restoration — Süleyman Aslan · 2026-09-23
- Quanta Explains How Pricing Algorithms Can Drive Up Prices Without Collusion — burny_tech · 2026-09-23
- CodeMidas: Turning Raw Source Code into Executable RL Environments for Coding Agents — burny_tech · 2026-09-23
- Researchers pine for pre-2000s methodological papers with no mathiness or defensive fluff — PMinervini · 2026-09-23
- Block-triangular joint drifting enables one-step generative surrogate models for stochastic trajectories — chaumian · 2026-09-23