Metraipolis › archive › dc_da04ba7ae5f7

First-Order Optimization as Minimum-Time Control — arXiv:2608.13915

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13915
License (as archived)
CC0-1.0
Archived
2026-10-19T04:15:35.824Z
SHA-256 of the archived text
6eca0d14d33bfa78ae7426760dbc7dab562611e1267177e4405c8590925ade49
Stable URL of this page
https://metraipolis.com/documento/dc_da04ba7ae5f7

How to cite

First-Order Optimization as Minimum-Time Control — arXiv:2608.13915 — arXiv (en), https://arxiv.org/abs/2608.13915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da04ba7ae5f7 (Metraipolis archive dc_da04ba7ae5f7, sha256 6eca0d14d33bfa78ae7426760dbc7dab562611e1267177e4405c8590925ade49)
BibTeX
@misc{dcda04ba7ae5f7,
  title = {First-Order Optimization as Minimum-Time Control — arXiv:2608.13915},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13915},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da04ba7ae5f7; sha256 6eca0d14d33bfa78ae7426760dbc7dab562611e1267177e4405c8590925ade49},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We formulate first-order optimization as a minimum-time control problem. The iterate is the state, the update, a combination of the gradients observed so far, is the control, and the points with gradient norm at most a prescribed tolerance form the target set. For a fixed objective and start, the minimum number of oracle queries needed to reach the target is a value function: it measures the complexity of the instance, not the worst case over a class. On a strongly convex quadratic, the conjugate gradient iterates emerge from the discrete Pontryagin conditions, and the value is a controllability index. Beyond the quadratic, a Hessian-generated reachable span replaces the controllability matrix, and feasibility becomes a reachability question: whether a critical point can be reached at all, and in how many steps, is read from the span. Curvature is a resource: a checkable condition certifies that an instance needs fewer steps than the controllability index of its quadratic model at the minimizer, and the gap can grow without bound with the dimension. The value is thus a benchmark for the intrinsic difficulty of each instance, against which any first-order method can be measured.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-17 in eess.SY).
Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2608.13915 — 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 2026-10-19T04:11:46.932Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).