Metraipolis › archive › dc_06bc43294cac

Randomized and Oracle-Based Feasible Directions Methods for Nonsmooth Nonconvex Constrained Optimization — arXiv:2611.07691

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07691
License (as archived)
CC0-1.0
Archived
2026-11-06T14:51:13.635Z
SHA-256 of the archived text
cfb6251da91bb0dcd3f9fc284439cb4e199abc178ca8e6dfe627a31bd3fda182
Stable URL of this page
https://metraipolis.com/documento/dc_06bc43294cac

How to cite

Randomized and Oracle-Based Feasible Directions Methods for Nonsmooth Nonconvex Constrained Optimization — arXiv:2611.07691 — arXiv (en), https://arxiv.org/abs/2611.07691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06bc43294cac (Metraipolis archive dc_06bc43294cac, sha256 cfb6251da91bb0dcd3f9fc284439cb4e199abc178ca8e6dfe627a31bd3fda182)
BibTeX
@misc{dc06bc43294cac,
  title = {Randomized and Oracle-Based Feasible Directions Methods for Nonsmooth Nonconvex Constrained Optimization — arXiv:2611.07691},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07691},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06bc43294cac; sha256 cfb6251da91bb0dcd3f9fc284439cb4e199abc178ca8e6dfe627a31bd3fda182},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Minimizing nonsmooth nonconvex objectives over general convex sets using no derivatives of the objective, together with structural access to the constraint set, poses a fundamental geometric difficulty: at boundary points, the feasible direction cone may fail to be closed, preventing the construction of finite sets of search directions that capture all feasible descent directions. We develop a feasible-directions framework for problems structured as the difference between a continuously differentiable function and a convex function over a closed convex set, and access the objective without knowledge of its decomposition, through exact line searches along feasible segments. To address the geometric obstruction, we introduce $\eta$-feasible directions, which remain uniformly separated from the boundary of the feasible direction cone, enabling finite-direction search even in the presence of nonlinear constraints. We present two algorithmic realizations of this framework. The first assumes access to an $\eta$-direction oracle and extends feasible-directions methods from linear to general convex constraints. The second replaces the oracle by a noise-augmented randomization scheme that constructs spanning directions from the affine-hull inner normal and almost surely avoids nonsmooth boundary points when initialized outside that set. Under curvature bounds and Lipschitz continuity of the smooth component's gradient, we jointly control the spanning coefficients and feasible step lengths of the oracle construction. This yields finite-time approximate $d$-stationarity along every unit feasible direction admitting a prescribed positive step length. For both methods, we also establish a rate in the proximal directional minimization (PDM) measure, assuming uniformly bounded direction-set sizes. Randomized exploration ensures that, almost surely, every accumulation point is $d$-stationary.

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).
Pagina del lavoro: https://arxiv.org/abs/2611.07691 — 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 2026-11-06T14:21:42.662Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).