Metraipolis › archive › dc_a4a4e8bacbf7

Conic-Lifting for Learning-rate-free Convex Optimization — arXiv:2610.39531

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39531
License (as archived)
CC0-1.0
Archived
2026-11-01T02:27:10.231Z
SHA-256 of the archived text
6c51a176f11343ff44b7666dda3d55923a93af641d80e2440b3aa2dc41061332
Stable URL of this page
https://metraipolis.com/documento/dc_a4a4e8bacbf7

How to cite

Conic-Lifting for Learning-rate-free Convex Optimization — arXiv:2610.39531 — arXiv (en), https://arxiv.org/abs/2610.39531 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4a4e8bacbf7 (Metraipolis archive dc_a4a4e8bacbf7, sha256 6c51a176f11343ff44b7666dda3d55923a93af641d80e2440b3aa2dc41061332)
BibTeX
@misc{dca4a4e8bacbf7,
  title = {Conic-Lifting for Learning-rate-free Convex Optimization — arXiv:2610.39531},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39531},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4a4e8bacbf7; sha256 6c51a176f11343ff44b7666dda3d55923a93af641d80e2440b3aa2dc41061332},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39531. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A central topic in online and stochastic optimization is to design algorithms that do not require tuning of hyperparameters. Successful strategies in online learning include AdaGrad-style learning rates, Conic Blackwell algorithms, and parameter-free algorithms. However, these classes require different, often difficult, analyses. We develop a unifying family of Online Convex Optimization (OCO) algorithms that require no user-tuned learning rate on convex domains that may be unbounded. The construction lifts the domain to a cone by adding one scalar coordinate, an idea going back to Blackwell (1954). The lifted subgradients are orthogonal to the corresponding lifted decisions, leaving the comparator scale free to optimize in the regret analysis. Applying Follow-the-Regularized-Leader (FTRL) and Online Mirror Descent (OMD) on the cone recovers Conic Blackwell Algorithm (CBA) and Conic Blackwell Algorithm Plus (CBA$^+$) on bounded domains in Hilbert spaces and extends them to finite-dimensional normed spaces with a strongly convex squared norm. For arbitrary nonempty closed convex domains in these spaces, a known gradient bound yields parameter-free regret guarantees. Surprisingly, on an unconstrained Hilbert space, the construction recovers the Krichevsky--Trofimov (KT) coin-betting algorithm exactly. We also give a parameter-free algorithm for unconstrained domains that requires no gradient bound.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.39531 — 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 2026-11-01T02:12:44.299Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).