arXiv Machine Learning

Omniprediction for All Mixable Proper Losses and Beyond

arXiv:2610. 41023v1 Announce Type: new Abstract: Omniprediction concerns the task of making predictions that are simultaneously accurate with respect to different losses.

arXiv Machine Learning
Aug 12

High-Dimensional Calibration from Swap Regret

arXiv:2505. 21460v2 Announce Type: replace Abstract: We study online calibration of multi-dimensional forecasts over an arbitrary convex set $P \subset \mathbb{R}^d$ relative to an arbitrary norm $|\cdot|$.

By Maxwell Fishelson, Noah Golowich, Mehryar Mohri, Jon Schneider