Maxwell Fishelson

activity

20202026

most citedNear-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games

17 citations · 27 across the 9 of their papers we have counts for

collaborators

Showing stat.MLShow all

2 papers · 1 filter

stat.ML2026

High-dimensional online calibration from harmonic weights

Maxwell Fishelson, Mehryar Mohri

We study the online calibration of multidimensional forecasts over an arbitrary convex set $Y \subseteq R^{d}$ relative to an arbitrary error norm $∥ \cdot ∥_{L}$ . For forecas…

stat.ML2026

Explicit Asymptotic Bounds for Sequential Calibration Beyond $T^{2/3}$

Eric Dai, Maxwell Fishelson

Probability forecasts are calibrated when predicted probabilities match empirical outcome frequencies: among events assigned a probability $p$ , we'd hope that the fraction of posit…

High-dimensional online calibration from harmonic weights

Explicit Asymptotic Bounds for Sequential Calibration Beyond T2/3

Explicit Asymptotic Bounds for Sequential Calibration Beyond $T^{2/3}$