Pith. sign in

REVIEW 3 cited by

An Adaptive Policy to Employ Sharpness-Aware Minimization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2304.14647 v1 pith:EAHRYKJB submitted 2023-04-28 cs.LG

Weisen Jiang , Hansi Yang , Yu Zhang , James Kwok This is my paper · ORCID
classification cs.LG
keywords adaptiveminimizationpolicyae-samemploysharpness-awareupdatesaccelerate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Sharpness-aware minimization (SAM), which searches for flat minima by min-max optimization, has been shown to be useful in improving model generalization. However, since each SAM update requires computing two gradients, its computational cost and training time are both doubled compared to standard empirical risk minimization (ERM). Recent state-of-the-arts reduce the fraction of SAM updates and thus accelerate SAM by switching between SAM and ERM updates randomly or periodically. In this paper, we design an adaptive policy to employ SAM based on the loss landscape geometry. Two efficient algorithms, AE-SAM and AE-LookSAM, are proposed. We theoretically show that AE-SAM has the same convergence rate as SAM. Experimental results on various datasets and architectures demonstrate the efficiency and effectiveness of the adaptive policy.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Preconditioned Sharpness-Aware Minimization: Unifying Analysis and a Novel Learning Algorithm

    cs.LG 2025-01 conditional novelty 7.0 of 10

    A preconditioning framework unifies several sharpness-aware minimization algorithms, and the new infoSAM variant achieves small accuracy gains across image benchmarks.

  2. Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization

    cs.LG 2026-07 conditional novelty 5.0 of 10

    GEAR-SAM re-allocates SAM's fixed perturbation radius across network blocks in proportion to an EMA of squared block-gradient norms, improving generalization on CIFAR, transfer, and label-noise benchmarks.

  3. VASSO: Variance Suppression for Sharpness-Aware Minimization

    cs.LG 2025-09 conditional novelty 4.0 of 10

    VASSO replaces SAM's minibatch gradient with an exponential moving average of past gradients when computing the adversarial perturbation, improving generalization across vision and language tasks.

Pith tools