Oracle Efficient Online Multicalibration and Omniprediction
Sumegha Garg, Christopher Jung, Omer Reingold, Aaron Roth

TL;DR
This paper introduces the first efficient online omnipredictor that extends multicalibration to infinite classes, providing simultaneous guarantees for various loss functions in an adversarial online setting.
Contribution
It develops an oracle efficient online multicalibration algorithm for infinite classes, enabling the first efficient online omnipredictor with broad loss guarantees.
Findings
First efficient online omnipredictor for infinite classes.
Proves swap-omniprediction is impossible at O(√T) rates.
Provides a non-oracle algorithm achieving optimal O(√T) bounds.
Abstract
A recent line of work has shown a surprising connection between multicalibration, a multi-group fairness notion, and omniprediction, a learning paradigm that provides simultaneous loss minimization guarantees for a large family of loss functions. Prior work studies omniprediction in the batch setting. We initiate the study of omniprediction in the online adversarial setting. Although there exist algorithms for obtaining notions of multicalibration in the online adversarial setting, unlike batch algorithms, they work only for small finite classes of benchmark functions , because they require enumerating every function at every round. In contrast, omniprediction is most interesting for learning theoretic hypothesis classes , which are generally continuously large. We develop a new online multicalibration algorithm that is well defined for infinite benchmark classes ,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research · Adversarial Robustness in Machine Learning · Machine Learning and Algorithms
