stat.MLFeb 3, 2026

Online Conformal Prediction via Universal Portfolio Algorithms

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) seeks prediction intervals that achieve long-run 1−α1-α coverage for arbitrary (possibly adversarial) data streams, while remaining as informative as possible. Existing OCP methods often require manual learning-rate tuning to work well, and may also require algorithm-specific analyses. Here, we develop a general regret-to-coverage theory for interval-valued OCP based on the (1−α)(1-α)-pinball loss. Our first contribution is to identify linearized regret as a key notion, showing that controlling it implies coverage bounds for any online algorithm. This relies on a black-box reduction that depends only on the Fenchel conjugate of an upper bound on the linearized regret. Building on this theory, we propose UP-OCP, a parameter-free method for OCP, via a reduction to a two-asset portfolio selection problem, leveraging universal portfolio algorithms. We show strong finite-time bounds on the miscoverage of UP-OCP, even for polynomially growing predictions. Extensive experiments support that UP-OCP delivers consistently better size/coverage trade-offs than prior online conformal baselines.

Figures & tables

Appendix figures & tables60 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Black-Box Reduction from Regret to Multi-Level Coverage

    Nov 9, 2026Tuo Liu, Edgar Dobriban, Francesco OrabonaConformal PredictionRegression Prediction Intervals

  2. Online Conformal Prediction Beyond Feedback

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

  3. Counterfactual Online Conformal Prediction Under Adaptive Logging

    Sep 25, 2026Xinyu Qiao, Yichen Lin, Kaihong Ji +2Conformal PredictionWeighted Conformal Prediction