Pith Number

pith:NV7UHJFD

pith:2020:NV7UHJFDR4W2SSP6STKYGLA6HM

not attested not anchored not stored refs resolved

Sharpness-Aware Minimization for Efficiently Improving Generalization

Ariel Kleiner, Behnam Neyshabur, Hossein Mobahi, Pierre Foret

Sharpness-Aware Minimization finds parameters in flat loss neighborhoods to improve generalization over standard training.

arxiv:2010.01412 v3 · 2020-10-03 · cs.LG · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{NV7UHJFDR4W2SSP6STKYGLA6HM}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

SAM improves model generalization across a variety of benchmark datasets (e.g., CIFAR-10, CIFAR-100, ImageNet, finetuning tasks) and models, yielding novel state-of-the-art performance for several.

C2weakest assumption

That seeking parameters whose neighborhoods have uniformly low loss will reliably produce better generalization than standard training; this is motivated by prior geometry work but is not derived from first principles in the given text.

C3one line summary

SAM solves a min-max problem to locate flat low-loss regions, improving generalization on CIFAR, ImageNet and label-noise tasks.

References

47 extracted · 47 resolved · 27 Pith anchors

[1] URL https://openreview.net/forum? id=BJl6t64tvr. 8https://github.com/google/spectral-density 9https://github.com/davda54/sam 9 Published as a conference paper at ICLR 2021 James Bradbury, Roy Frostig, 2021

[2] Entropy-sgd: Biasing gradient descent into wide valleys · arXiv:1611.01838

[4] Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels 1905 · arXiv:1905.05040

[5] AutoAugment: Learning Augmentation Policies from Data · arXiv:1805.09501

[7] Improved Regularization of Convolutional Neural Networks with Cutout · arXiv:1708.04552

Formal links

2 machine-checked theorem links

Cited by

29 papers in Pith

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction

Optimization Hyper-parameter Laws for Large Language Models

Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control

UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shifts

Pointwise Generalization in Deep Neural Networks

Receipt and verification

First computed	2026-05-17T23:38:46.718537Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6d7f43a4a38f2da949fe94d5832c1e3b0a8dac65f77f6d69d6179b8522363e26

Aliases

arxiv: 2010.01412 · arxiv_version: 2010.01412v3 · doi: 10.48550/arxiv.2010.01412 · pith_short_12: NV7UHJFDR4W2 · pith_short_16: NV7UHJFDR4W2SSP6 · pith_short_8: NV7UHJFD

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/NV7UHJFDR4W2SSP6STKYGLA6HM \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 6d7f43a4a38f2da949fe94d5832c1e3b0a8dac65f77f6d69d6179b8522363e26

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2ce3a0bcb0d779ae72b8453f52ce832d42d216560b87c0217e2a7ea682c6faf5",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2020-10-03T19:02:10Z",
    "title_canon_sha256": "ef695ff56cc3a20597397d65478da7519df22170ecb76f4f10fc267a546d1130"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2010.01412",
    "kind": "arxiv",
    "version": 3
  }
}