AI RESEARCH
Instance-Adaptive Online Multicalibration
arXiv CS.LG
•
ArXi:2605.09273v1 Announce Type: new 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.