Saved in:
Bibliographic Details
Main Authors: Liu, Tuo, Dobriban, Edgar, Orabona, Francesco
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.03168
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914303892783104
author Liu, Tuo
Dobriban, Edgar
Orabona, Francesco
author_facet Liu, Tuo
Dobriban, Edgar
Orabona, Francesco
contents Online conformal prediction (OCP) seeks prediction intervals that achieve long-run $1-α$ 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 $(1-α)$-pinball loss. Our first contribution is to identify \emph{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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03168
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Online Conformal Prediction via Universal Portfolio Algorithms
Liu, Tuo
Dobriban, Edgar
Orabona, Francesco
Machine Learning
Online conformal prediction (OCP) seeks prediction intervals that achieve long-run $1-α$ 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 $(1-α)$-pinball loss. Our first contribution is to identify \emph{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.
title Online Conformal Prediction via Universal Portfolio Algorithms
topic Machine Learning
url https://arxiv.org/abs/2602.03168