ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2302.06726
11
15

Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration

13 February 2023
Parikshit Gopalan
Michael P. Kim
Omer Reingold
ArXivPDFHTML
Abstract

We introduce and study Swap Agnostic Learning. The problem can be phrased as a game between a predictor and an adversary: first, the predictor selects a hypothesis hhh; then, the adversary plays in response, and for each level set of the predictor {x∈X:h(x)=v}\{x \in \mathcal{X} : h(x) = v\}{x∈X:h(x)=v} selects a (different) loss-minimizing hypothesis cv∈Cc_v \in \mathcal{C}cv​∈C; the predictor wins if hhh competes with the adaptive adversary's loss. Despite the strength of the adversary, we demonstrate the feasibility Swap Agnostic Learning for any convex loss. Somewhat surprisingly, the result follows through an investigation into the connections between Omniprediction and Multicalibration. Omniprediction is a new notion of optimality for predictors that strengthtens classical notions such as agnostic learning. It asks for loss minimization guarantees (relative to a hypothesis class) that apply not just for a specific loss function, but for any loss belonging to a rich family of losses. A recent line of work shows that omniprediction is implied by multicalibration and related multi-group fairness notions. This unexpected connection raises the question: is multi-group fairness necessary for omniprediction? Our work gives the first affirmative answer to this question. We establish an equivalence between swap variants of omniprediction and multicalibration and swap agnostic learning. Further, swap multicalibration is essentially equivalent to the standard notion of multicalibration, so existing learning algorithms can be used to achieve any of the three notions. Building on this characterization, we paint a complete picture of the relationship between different variants of multi-group fairness, omniprediction, and Outcome Indistinguishability. This inquiry reveals a unified notion of OI that captures all existing notions of omniprediction and multicalibration.

View on arXiv
Comments on this paper