Metraipolis › archive › dc_bd883caacc3b

FlexGrad: a root-free approach to adaptive step sizes — arXiv:2610.09203

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09203
License (as archived): CC0-1.0
Archived: 2026-10-08T12:40:24.897Z
SHA-256 of the archived text: 0c24c21d405d5e5e582433aa7d8f486d62bf0b752240ee529e98b07f4f5bce70
Stable URL of this page: https://metraipolis.com/documento/dc_bd883caacc3b

How to cite

FlexGrad: a root-free approach to adaptive step sizes — arXiv:2610.09203 — arXiv (en), https://arxiv.org/abs/2610.09203 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd883caacc3b (Metraipolis archive dc_bd883caacc3b, sha256 0c24c21d405d5e5e582433aa7d8f486d62bf0b752240ee529e98b07f4f5bce70)

BibTeX

@misc{dcbd883caacc3b,
  title = {FlexGrad: a root-free approach to adaptive step sizes — arXiv:2610.09203},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09203},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd883caacc3b; sha256 0c24c21d405d5e5e582433aa7d8f486d62bf0b752240ee529e98b07f4f5bce70},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09203. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce the FlexGrad optimizer, an adaptive gradient method that addresses a key limitation of classical AdaGrad-type methods: their inability to exploit correlations between gradients. By scaling steps using both cumulative gradients and cumulative squared gradients, FlexGrad preserves AdaGrad-like behavior in noisy regimes while allowing substantially larger steps when gradient directions are persistent. The method is fully online, horizon-free, and avoids any auxiliary search procedure during optimization. For convex Lipschitz objectives, we prove that FlexGrad attains the optimal asymptotic convergence rate for nonsmooth convex optimization, with guarantees for both global and coordinate-wise variants. FlexGrad is straightforward to implement and is closely connected to practical gradient-normalized methods. Experiments on a range of convex and nonconvex problems show that FlexGrad performs competitively across a range of optimization settings.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.09203 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:16:00.172Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).