← 研踪 PaperTrailarXiv:2611.12059 · v1
A Black-Box Reduction from Regret to Multi-Level Coverage
首次提交 2026-11-09 16:34
版本更新 2026-11-09 16:34
雷达观测 2026-11-10 15:22
摘要
Online Conformal Prediction (OCP) sequentially constructs prediction sets whose average empirical coverage converges to a target level over time, for arbitrary, potentially adversarial datasets. In the multi-level setting, prediction sets are produced at coverage levels at once. Prior work argued for the use of online gradient descent with isotonic projections, which produces sets nested across levels, but with a dependence in the per-level coverage convergence rate. Here, we both generalize and improve prior work. First, we show that isotonic projections can be used for the construction of multi-level online conformal prediction sets from \emph{any} online learning algorithm (not just gradient descent). Then, through a black-box reduction, we show that the linearized regret of the online algorithm itself automatically gives control over both per-level coverage and distributional consistency of multi-level predictions via Fenchel duality. Finally, by using the Weighted Interval Score, a standard scoring rule for assessing multi-level interval forecasts, we prove that these projections reduce both the size of the sets and their under-coverage. We study two instantiations of our theory, -norm Online Mirror Descent and coordinate-wise Universal Portfolio methods, both improving the dependence on the number of levels to for the multi-level OCP problem. Experiments on several datasets show favorable performance compared to baselines.
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。
v1 · 2026-11-09 16:34 · 最新观测版本
A Black-Box Reduction from Regret to Multi-Level Coverage
Online Conformal Prediction (OCP) sequentially constructs prediction sets whose average empirical coverage converges to a target level over time, for arbitrary, potentially adversarial datasets. In the multi-level setting, prediction sets are produced at coverage levels at once. Prior work argued for the use of online gradient descent with isotonic projections, which produces sets nested across levels, but with a dependence in the per-level coverage convergence rate. Here, we both generalize and improve prior work. First, we show that isotonic projections can be used for the construction of multi-level online conformal prediction sets from \emph{any} online learning algorithm (not just gradient descent). Then, through a black-box reduction, we show that the linearized regret of the online algorithm itself automatically gives control over both per-level coverage and distributional consistency of multi-level predictions via Fenchel duality. Finally, by using the Weighted Interval Score, a standard scoring rule for assessing multi-level interval forecasts, we prove that these projections reduce both the size of the sets and their under-coverage. We study two instantiations of our theory, -norm Online Mirror Descent and coordinate-wise Universal Portfolio methods, both improving the dependence on the number of levels to for the multi-level OCP problem. Experiments on several datasets show favorable performance compared to baselines.
查看此版本解读 →查看此版本原文 ↗