Pith. sign in

REVIEW 1 cited by

Risk Variance Penalization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.07544 v2 pith:YZ7JDGWX submitted 2020-06-13 cs.LG stat.ML

classification cs.LGstat.ML
keywords v-rexregularizationrisktheoreticalvariancedomainspenalizationpredictor
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains. The variance risk extrapolation (V-REx) is a practical OOD method, which depends on a domain-level regularization but lacks theoretical verifications about its motivation and utility. This article provides theoretical insights into V-REx by studying a variance-based regularizer. We propose Risk Variance Penalization (RVP), which slightly changes the regularization of V-REx but addresses the theory concerns about V-REx. We provide theoretical explanations and a theory-inspired tuning scheme for the regularization parameter of RVP. Our results point out that RVP discovers a robust predictor. Finally, we experimentally show that the proposed regularizer can find an invariant predictor under certain conditions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Achievable distributional robustness when the robust risk is only partially identified

    stat.ML 2025-02 conditional novelty 6.0 of 10

    In partially identified linear models, the worst-case robust risk yields a minimax predictor that abstains on unseen shift directions and provably outperforms anchor regression and OLS when test shifts include new directions.

Pith tools