Metraipolis › archive › dc_d0cdcfeec703

Subgradient Methods for Nonsmooth Sample Average Approximation — arXiv:2611.02534

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02534
License (as archived): CC0-1.0
Archived: 2026-11-03T11:31:29.164Z
SHA-256 of the archived text: 5a6927070caeb774d453233aee39e111846f172ccc84c920a6896ef2a019ba98
Stable URL of this page: https://metraipolis.com/documento/dc_d0cdcfeec703

How to cite

Subgradient Methods for Nonsmooth Sample Average Approximation — arXiv:2611.02534 — arXiv (en), https://arxiv.org/abs/2611.02534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0cdcfeec703 (Metraipolis archive dc_d0cdcfeec703, sha256 5a6927070caeb774d453233aee39e111846f172ccc84c920a6896ef2a019ba98)

BibTeX

@misc{dcd0cdcfeec703,
  title = {Subgradient Methods for Nonsmooth Sample Average Approximation — arXiv:2611.02534},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02534},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0cdcfeec703; sha256 5a6927070caeb774d453233aee39e111846f172ccc84c920a6896ef2a019ba98},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study direct subgradient methods for nonsmooth sample average approximation (SAA). Subgradient descent and Nesterov acceleration with constant step sizes attain polynomial and geometric rates matching their smooth counterparts. After $O(\log n)$ full-batch updates, where $n$ is the sample size, the computed solution has the same first-order expansion and limiting distribution as an SAA solution, even when the iterates do not converge. A bound on subgradient increments transfers population regularity to the sample objective, controls the algorithmic trajectory, and identifies the leading random term. The bound covers convex piecewise linear scenario costs, including two-stage stochastic linear programs with fixed recourse. Moreau smoothing displaces the population solution at first order and changes the limiting distribution of the computed solution. An explicit shift of the residual removes the first-order displacement and improves the expansion remainder. For sparse decisions, restricted increment bounds give convergence, support recovery, and expansions for proximal subgradient descent and iterative hard thresholding.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.CO, nuovi lavori del giorno).
Categorie arXiv: Computation (stat.CO) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.02534 — 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 2026-11-03T11:04:07.131Z dalla pagina https://arxiv.org/list/stat.CO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).