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. 2101.01739
44
39

Online Multivalid Learning: Means, Moments, and Prediction Intervals

5 January 2021
Varun Gupta
Christopher Jung
Georgy Noarov
Mallesh M. Pai
Aaron Roth
ArXivPDFHTML
Abstract

We present a general, efficient technique for providing contextual predictions that are "multivalid" in various senses, against an online sequence of adversarially chosen examples (x,y)(x,y)(x,y). This means that the resulting estimates correctly predict various statistics of the labels yyy not just marginally -- as averaged over the sequence of examples -- but also conditionally on x∈Gx \in Gx∈G for any GGG belonging to an arbitrary intersecting collection of groups G\mathcal{G}G. We provide three instantiations of this framework. The first is mean prediction, which corresponds to an online algorithm satisfying the notion of multicalibration from Hebert-Johnson et al. The second is variance and higher moment prediction, which corresponds to an online algorithm satisfying the notion of mean-conditioned moment multicalibration from Jung et al. Finally, we define a new notion of prediction interval multivalidity, and give an algorithm for finding prediction intervals which satisfy it. Because our algorithms handle adversarially chosen examples, they can equally well be used to predict statistics of the residuals of arbitrary point prediction methods, giving rise to very general techniques for quantifying the uncertainty of predictions of black box algorithms, even in an online adversarial setting. When instantiated for prediction intervals, this solves a similar problem as conformal prediction, but in an adversarial environment and with multivalidity guarantees stronger than simple marginal coverage guarantees.

View on arXiv
Comments on this paper