Pith. sign in

REVIEW 1 cited by

Shift-Curvature, SGD, and 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 2108.09507 v3 pith:VE3QWX6B submitted 2021-08-21 stat.ML cs.LG

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

A longstanding debate surrounds the related hypotheses that low-curvature minima generalize better, and that SGD discourages curvature. We offer a more complete and nuanced view in support of both. First, we show that curvature harms test performance through two new mechanisms, the shift-curvature and bias-curvature, in addition to a known parameter-covariance mechanism. The three curvature-mediated contributions to test performance are reparametrization-invariant although curvature is not. The shift in the shift-curvature is the line connecting train and test local minima, which differ due to dataset sampling or distribution shift. Although the shift is unknown at training time, the shift-curvature can still be mitigated by minimizing overall curvature. Second, we derive a new, explicit SGD steady-state distribution showing that SGD optimizes an effective potential related to but different from train loss, and that SGD noise mediates a trade-off between deep versus low-curvature regions of this effective potential. Third, combining our test performance analysis with the SGD steady state shows that for small SGD noise, the shift-curvature may be the most significant of the three mechanisms. Our experiments confirm the impact of shift-curvature on test loss, and further explore the relationship between SGD noise and curvature.

Discussion (0). Sign in 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. The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

    cs.LG 2025-06 conditional novelty 7.0 of 10

    A single-weight perturbation at the very start of training makes otherwise identical neural networks diverge to different loss basins, and this sensitivity drops sharply within the first fraction of training.

Pith tools