Metraipolis › archive › dc_a844f522df7a

Stochastic and Noisy Oracles in Smooth Continuous Optimization — arXiv:2610.41086

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41086
License (as archived)
CC0-1.0
Archived
2026-11-02T07:51:14.585Z
SHA-256 of the archived text
17a31b7f9a2eae97ecea36505d6eda5dc69df732556d867dfff295525480e409
Stable URL of this page
https://metraipolis.com/documento/dc_a844f522df7a

How to cite

Stochastic and Noisy Oracles in Smooth Continuous Optimization — arXiv:2610.41086 — arXiv (en), https://arxiv.org/abs/2610.41086 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a844f522df7a (Metraipolis archive dc_a844f522df7a, sha256 17a31b7f9a2eae97ecea36505d6eda5dc69df732556d867dfff295525480e409)
BibTeX
@misc{dca844f522df7a,
  title = {Stochastic and Noisy Oracles in Smooth Continuous Optimization — arXiv:2610.41086},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41086},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a844f522df7a; sha256 17a31b7f9a2eae97ecea36505d6eda5dc69df732556d867dfff295525480e409},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41086. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We review models of inexact computational oracles in smooth continuous optimization and their implications for the convergence, computational complexity, and attainable accuracy of optimization algorithms. We adopt a framework in which zeroth-,first-, and second-order oracles are characterized by quantitative error bounds and may accept additional control parameters that influence both their accuracy and computational cost. We introduce deterministic and stochastic oracle models and illustrate their properties through a variety of examples, including finite-difference approximations, stochastic gradients, and randomized derivative estimators. Particular attention is given to the distinction between absolute and relative errors, bias and variance, and stochastic function evaluations with independent or coupled randomness. A central theme of the review is the use of common analytical tools to recover and compare convergence and complexity guarantees under different oracle models. For deterministic and stochastic first-order methods, we show how a general descent inequality leads to complexity bounds under various assumptions on the objective function and all proposed oracle models. In the stochastic setting, we develop bounds on expected stopping times and the accuracy that can be guaranteed under different oracle conditions. We also examine the total computational complexity of algorithms relying on specific oracle constructions and briefly review models of inexact second- order information and their use in optimization algorithms.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Computational Complexity (cs.CC); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41086 — 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 2026-11-02T07:40:00.246Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).