Pith. sign in

REVIEW 2 cited by

Provable Weak-to-Strong Generalization via Benign Overfitting

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 2410.04638 v2 pith:NPNT5JPF submitted 2024-10-06 cs.LG stat.ML

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

The classic teacher-student model in machine learning posits that a strong teacher supervises a weak student to improve the student's capabilities. We instead consider the inverted situation, where a weak teacher supervises a strong student with imperfect pseudolabels. This paradigm was recently brought forth by Burns et al.'23 and termed \emph{weak-to-strong generalization}. We theoretically investigate weak-to-strong generalization for binary and multilabel classification in a stylized overparameterized spiked covariance model with Gaussian covariates where the weak teacher's pseudolabels are asymptotically like random guessing. Under these assumptions, we provably identify two asymptotic phases of the strong student's generalization after weak supervision: (1) successful generalization and (2) random guessing. Our techniques should eventually extend to weak-to-strong multiclass classification. Towards doing so, we prove a tight lower tail inequality for the maximum of correlated Gaussians, which may be of independent interest. Understanding the multilabel setting reinforces the value of using logits for weak supervision when they are available.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions

    cs.LG 2025-02 conditional novelty 8.0 of 10

    Weak-to-strong performance is governed by the overlap between the weak model's unlearnable error space and the strong model's principal-representation space, quantified by ||P_s(I-P_w)||.

  2. Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss

    cs.LG 2025-01 conditional novelty 6.0 of 10

    For convex and approximately convex model classes, the loss gain in weak-to-strong learning is at least the KL misfit between strong and weak models, plus an error term that vanishes as k grows.

Pith tools