Pith. sign in

REVIEW 4 cited by

Understanding the Failure Modes of Out-of-Distribution Generalization

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 2010.15775 v3 pith:XSXZJ7ML submitted 2020-10-29 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords modesfailuremodelsarisedatasetsduringeasy-to-learnnature
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Empirical studies suggest that machine learning models often rely on features, such as the background, that may be spuriously correlated with the label only during training time, resulting in poor accuracy during test-time. In this work, we identify the fundamental factors that give rise to this behavior, by explaining why models fail this way {\em even} in easy-to-learn tasks where one would expect these models to succeed. In particular, through a theoretical study of gradient-descent-trained linear classifiers on some easy-to-learn tasks, we uncover two complementary failure modes. These modes arise from how spurious correlations induce two kinds of skews in the data: one geometric in nature, and another, statistical in nature. Finally, we construct natural modifications of image classification datasets to understand when these failure modes can arise in practice. We also design experiments to isolate the two failure modes when training modern neural networks on these datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 50 citations worldwide. Full citation record

  1. The Pitfalls of Memorization: When Memorization Hurts Generalization

    cs.LG 2024-12 conditional novelty 6.0 of 10

    Memorization-aware training (MAT) shifts logits using calibrated held-out predictions from an XRM auxiliary model, improving worst-group accuracy under subpopulation shift.

  2. Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

    cs.LG 2025-01 conditional novelty 5.0 of 10

    Causal reward modeling applies MMD regularization to RLHF reward models to make reward scores statistically independent of spurious features, reducing measured length, sycophancy, concept, and demographic biases in ex...

  3. Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation

    cs.LG 2024-12 accept novelty 5.0 of 10

    A unifying taxonomy and formal definition that connects shortcut learning, spurious correlations, Clever Hans behavior, and confounders across detection, mitigation, and datasets.

  4. Weight Averaging for Out-of-Distribution Generalization and Few-Shot Domain Adaptation

    cs.CV 2025-01 reject novelty 4.0 of 10

    Gradient-similarity-regularized weight averaging and WA+SAM fine-tuning are tested on OOD and few-shot domain adaptation benchmarks, with mixed results that do not support the claimed improvements.

Pith tools