Metraipolis › archive › dc_abb0cc9436bd

A Sharper Theory of Ball-Proximal Optimization: Convergence and Radius Selection — arXiv:2609.35147

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35147
License (as archived)
CC0-1.0
Archived
2026-10-07T23:06:46.670Z
SHA-256 of the archived text
12d677a069f3fcf78dbb36c71a6e935b036d41516b47c6065f5beb4fd3e3c85e
Stable URL of this page
https://metraipolis.com/documento/dc_abb0cc9436bd

How to cite

A Sharper Theory of Ball-Proximal Optimization: Convergence and Radius Selection — arXiv:2609.35147 — arXiv (en), https://arxiv.org/abs/2609.35147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_abb0cc9436bd (Metraipolis archive dc_abb0cc9436bd, sha256 12d677a069f3fcf78dbb36c71a6e935b036d41516b47c6065f5beb4fd3e3c85e)
BibTeX
@misc{dcabb0cc9436bd,
  title = {A Sharper Theory of Ball-Proximal Optimization: Convergence and Radius Selection — arXiv:2609.35147},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35147},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_abb0cc9436bd; sha256 12d677a069f3fcf78dbb36c71a6e935b036d41516b47c6065f5beb4fd3e3c85e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the exact Euclidean ball-proximal point method for proper, closed, convex functions, where each iteration minimizes the objective over a ball centered at the current point. Retaining the objective gap in the decrease of squared distance yields sharper bounds on objective values, stationarity, and the symmetric Bregman distance to a minimizer. For constant radius $t>0$ and initial distance $D_0>0$ to the solution set, the objective gap after $K$ iterations is at most its initial value multiplied by $\exp(-2K^2t^2/D_0^2)$. We characterize convergence for arbitrary positive radius sequences. If their sum diverges, the method reaches a minimizer in finitely many iterations whenever one exists; otherwise, the objective values converge to the infimum and the iterates escape every bounded set. If the radii are summable, the iterates converge to a possibly nonoptimal point. Self-contraction gives finite trajectory length for bounded iterates and a constant-radius termination bound $O_d(1+D_0/t)$, whose implicit constant depends only on the dimension. A polyhedral family shows that the dimension-independent quadratic bound remains asymptotically sharp. We also identify a minimum successful geometric decay factor and analyze adaptive radius rules based on subgradients or objective gaps, epigraph reformulation, and relaxed updates. Together, these results strengthen the foundations and convergence guarantees of the method without assuming smoothness or strong convexity.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-29 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.35147 — 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 2026-10-07T22:42:39.270Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).