Pith. sign in

REVIEW 1 cited by

Does Invariant Risk Minimization Capture Invariance?

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 2101.01134 v2 pith:NV2JPTYE submitted 2021-01-04 stat.ML cs.AIcs.LG

classification stat.MLcs.AIcs.LG
keywords evenwheninvariantcaptureenvironmentsformulationinvarianceinvariances
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture "natural" invariances, at least when used in its practical "linear" form, and even on very simple problems which directly follow the motivating examples for IRM. This can lead to worse generalization on new environments, even when compared to unconstrained ERM. The issue stems from a significant gap between the linear variant (as in their concrete method IRMv1) and the full non-linear IRM formulation. Additionally, even when capturing the "right" invariances, we show that it is possible for IRM to learn a sub-optimal predictor, due to the loss function not being invariant across environments. The issues arise even when measuring invariance on the population distributions, but are exacerbated by the fact that IRM is extremely fragile to sampling.

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. Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization

    cs.LG 2025-06 reject novelty 6.0 of 10

    A unified moment-alignment theory bounds target-domain error by cross-domain differences in loss derivatives, and the new CMA algorithm implements exact gradient and Hessian matching in closed form.

Pith tools