← 研踪 PaperTrailarXiv:2605.11490 · v3
Adaptive Calibration in Non-Stationary Environments
首次提交 2026-05-12 12:06
版本更新 2026-11-13 12:06
雷达观测 2026-11-17 04:57
摘要
Making calibrated online predictions is a central challenge in modern AI systems. Much of the existing literature focuses on fully adversarial environments where outcomes may be arbitrary, leading to conservative algorithms that can perform suboptimally in more benign settings, such as when outcomes are nearly stationary. This gap raises a natural question: can we design online prediction algorithms whose calibration error automatically adapts to the degree of non-stationarity in the environment, smoothly interpolating between i.i.d. and adversarial regimes? We answer this question in the affirmative and develop a suite of algorithms that achieve adaptive calibration guarantees under multiple calibration measures. Specifically, with being the number of rounds, being the unknown number of i.i.d. segments of the environment, and being another unknown non-stationary measure defined as the minimal deviation of the mean outcomes, our algorithms attain for calibration error and for both and pseudo KL calibration error. These bounds match the optimal rates in the stationary case ( and ) and recover known guarantees in the fully adversarial regime (). Our approach builds on and extends prior work (Hu et al., 2026; Luo et al., 2025), introducing an epoch-based scheduling together with a novel non-uniform partition of the prediction space that allocates finer resolution near the underlying ground truth.
作者备注:50 pages, NeurIPS 2026
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-13 12:06 · 最新观测版本
Adaptive Calibration in Non-Stationary Environments
Making calibrated online predictions is a central challenge in modern AI systems. Much of the existing literature focuses on fully adversarial environments where outcomes may be arbitrary, leading to conservative algorithms that can perform suboptimally in more benign settings, such as when outcomes are nearly stationary. This gap raises a natural question: can we design online prediction algorithms whose calibration error automatically adapts to the degree of non-stationarity in the environment, smoothly interpolating between i.i.d. and adversarial regimes? We answer this question in the affirmative and develop a suite of algorithms that achieve adaptive calibration guarantees under multiple calibration measures. Specifically, with being the number of rounds, being the unknown number of i.i.d. segments of the environment, and being another unknown non-stationary measure defined as the minimal deviation of the mean outcomes, our algorithms attain for calibration error and for both and pseudo KL calibration error. These bounds match the optimal rates in the stationary case ( and ) and recover known guarantees in the fully adversarial regime (). Our approach builds on and extends prior work (Hu et al., 2026; Luo et al., 2025), introducing an epoch-based scheduling together with a novel non-uniform partition of the prediction space that allocates finer resolution near the underlying ground truth.
查看此版本解读 →查看此版本原文 ↗