Metraipolis › archive › dc_d9269cc2ffd2

Distributed Grid Search for Hyperparameter Tuning — arXiv:2610.41537

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41537
License (as archived)
CC0-1.0
Archived
2026-11-03T07:09:16.800Z
SHA-256 of the archived text
dfc4e60c25fb2d3bf6e98a63080dd70c343fd3b9536784e6923dce1744b16830
Stable URL of this page
https://metraipolis.com/documento/dc_d9269cc2ffd2

How to cite

Distributed Grid Search for Hyperparameter Tuning — arXiv:2610.41537 — arXiv (en), https://arxiv.org/abs/2610.41537 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9269cc2ffd2 (Metraipolis archive dc_d9269cc2ffd2, sha256 dfc4e60c25fb2d3bf6e98a63080dd70c343fd3b9536784e6923dce1744b16830)
BibTeX
@misc{dcd9269cc2ffd2,
  title = {Distributed Grid Search for Hyperparameter Tuning — arXiv:2610.41537},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41537},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9269cc2ffd2; sha256 dfc4e60c25fb2d3bf6e98a63080dd70c343fd3b9536784e6923dce1744b16830},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41537. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The performance of many distributed optimization algorithms over peer-to-peer networks strongly depends on the choice of their hyperparameters. However, existing selection rules often require global quantities, yield conservative choices, or are tied to specific algorithms and hyperparameters. We propose Distributed Grid Search (D-GS), a consensus-based search method that evaluates and selects hyperparameter configurations across the network, requiring only the ability to run the tuned algorithm and evaluate local gradients. We also propose a zoom-in variant, Distributed Zoom Grid Search (D-ZGS), which improves empirical performance at a reduced cost. We prove that both methods terminate in finite time with all agents holding the same hyperparameter configuration, and quantify the (sub)optimality of this configuration. Numerical experiments on linear and logistic regression show that D-GS closely matches a centralized reference and that tuning and deployment cost a fraction of deploying algorithms with hyperparameters tuned using theoretical results.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.41537 — 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 2026-11-03T07:09:16.744Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).