Instance-Adaptive Online Multicalibration
Abstract
We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-case sequences by adaptively refining a dyadic grid of prediction values. Its error is controlled by the number of leaves in the refinement tree. Our analysis recovers the known worst-case-optimal rate for online multicalibration, while simultaneously automatically adapting to easier instances: in the marginal stochastic setting it obtains a rate of , and for piecewise-stationary means with segments its rate is . More generally, the rate depends on a threshold-complexity measure of the predictable mean process relative to the group family. We show that this dependence is tight up to logarithmic factors.
Cite
@article{arxiv.2605.09273,
title = {Instance-Adaptive Online Multicalibration},
author = {Zhiming Huang and Jamie Morgenstern and Aaron Roth and Claire Jie Zhang},
journal= {arXiv preprint arXiv:2605.09273},
year = {2026}
}
Comments
We tightened the analysis and added a comparison to the concurrent work of Liu et al. (arXiv:2605.11490)