pith. sign in
Pith Number

pith:U24CT4MQ

pith:2026:U24CT4MQP5AJCAB2YLOHD5SEGJ
not attested not anchored not stored refs resolved

Auto-Conditioned Frank-Wolfe Algorithms

Khanh-Hung Giang-Tran, Nam Ho-Nguyen, Soroosh Shafiee

Frank-Wolfe methods converge with local Lipschitz estimates alone

arxiv:2605.15512 v1 · 2026-05-15 · math.OC

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{U24CT4MQP5AJCAB2YLOHD5SEGJ}

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

We develop a fully auto-conditioned framework for Frank-Wolfe-type methods that replaces the global Lipschitz constant in closed-loop step sizes with a local Lipschitz estimator computed from first-order information along the iterates, establishing convergence to stationary points in the nonconvex setting and recovering standard sublinear convergence guarantees in the convex setting without requiring prior knowledge of a global smoothness constant.

C2weakest assumption

The local Lipschitz estimator computed from first-order information along the iterates is accurate enough to serve as a drop-in replacement for the global smoothness constant while preserving the convergence analysis for the general class of methods including standard Frank-Wolfe, Matching Pursuit, pairwise Frank-Wolfe, and away-step Frank-Wolfe.

C3one line summary

Auto-conditioned Frank-Wolfe methods use local Lipschitz estimators from first-order information to achieve convergence guarantees in convex and nonconvex settings without prior global smoothness knowledge.

References

63 extracted · 63 resolved · 4 Pith anchors

[1] A. Alacaoglu, A. Böhm, and Y. Malitsky. Beyond the golden ratio for variational inequality algorithms.Journal of Machine Learning Research, 24(172):1–33, 2023 2023
[2] A. Alacaoglu, Y. Malitsky, and V. Cevher. Convergence of adaptive algorithms for constrained weakly convex optimization. InAdvances in Neural Information Processing Systems, pages 14214– 14225, 2021 2021
[3] A. Ansari-Önnestam and Y. Malitsky. Adaptive gradient descent on Riemannian manifolds with nonnegative curvature.arXiv:2504.16724, 2025 2025
[4] A. Asuncion and D. Newman. The UCI Machine Learning Repository, 2007 2007
[5] A. Attia and T. Koren. SGD with AdaGrad stepsizes: Full adaptivity with high probability to unknown parameters, unbounded gradients and affine variance. InInternational Conference on Machine Learning, 2023
Receipt and verification
First computed 2026-05-20T00:01:02.434205Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

a6b829f1907f4091003ac2dc71f64432732a8a78d91a1200c6c0acf4aad94f41

Aliases

arxiv: 2605.15512 · arxiv_version: 2605.15512v1 · doi: 10.48550/arxiv.2605.15512 · pith_short_12: U24CT4MQP5AJ · pith_short_16: U24CT4MQP5AJCAB2 · pith_short_8: U24CT4MQ
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/U24CT4MQP5AJCAB2YLOHD5SEGJ \
  | 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: a6b829f1907f4091003ac2dc71f64432732a8a78d91a1200c6c0acf4aad94f41
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "b74a58b1eeb50e8240ead1010c73a830889254a5526c33c5cba261c955ae6a1a",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "math.OC",
    "submitted_at": "2026-05-15T01:12:32Z",
    "title_canon_sha256": "bf5c5e9023657c0d4a09ed07ac18952bc4da1203fac355640f03e7ae9a17e6f4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15512",
    "kind": "arxiv",
    "version": 1
  }
}