Paper shows swap agnostic learning is equivalent to multicalibration and omniprediction

Sauers_ · x · 2026-08-04

What the paper claims

The paper introduces Swap Agnostic Learning (SAL), framed as a game between a predictor and an adversary. The predictor picks a hypothesis, the adversary responds, and the predictor is considered successful if its hypothesis competes with the adversary’s loss across all level sets.

Main result

The authors show that SAL is feasible for any convex loss. The proof comes from connecting three notions:

They show that swap omniprediction and multicalibration are equivalent to SAL, and that swap multicalibration is essentially equivalent to standard multicalibration, so existing learning algorithms can achieve all three notions.

Broader implication

The paper also maps out the relationship between:

That yields a unified view of outcome indistinguishability that captures the existing omniprediction and multicalibration frameworks.

Original post →

More from Research

Research channel →