stat.MLNov 9, 2026

A Black-Box Reduction from Regret to Multi-Level Coverage

Authors: Tuo Liu, Edgar Dobriban, Francesco Orabona

Organizations: King Abdullah University of Science and Technology, Saudi Arabia · University of Pennsylvania, USA

Abstract

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 dd 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 d\sqrt{d} 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 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, pp-norm Online Mirror Descent and coordinate-wise Universal Portfolio methods, both improving the dependence on the number of levels to log⁡d\sqrt{\log d} for the multi-level OCP problem. Experiments on several datasets show favorable performance compared to baselines.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Online Conformal Prediction via Universal Portfolio Algorithms

    Feb 3, 2026Tuo Liu, Edgar Dobriban, Francesco OrabonaConformal PredictionRegression Prediction Intervals

  2. Online Conformal Prediction: Enforcing monotonicity via Online Optimization

    May 12, 2026Eduardo Ochoa Rivera, Ambuj TewariConformal PredictionUncertainty Calibration

  3. Online Conformal Prediction Beyond Feedback

    Aug 7, 2026Joar Skalse, Edoardo Pona, Osvaldo Simeone +1Uncertainty QuantificationConformal Prediction