Metraipolis › archive › dc_394d64c1cdbb

Continuized Quasar-Convex Acceleration via an Unbiased Finite-Mixing Network Oracle — arXiv:2611.04597

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04597
License (as archived)
CC0-1.0
Archived
2026-11-04T21:56:03.924Z
SHA-256 of the archived text
69129799f65a276cf16cb07b2531f89efa9c7f23263e658145a9649ddc9647f2
Stable URL of this page
https://metraipolis.com/documento/dc_394d64c1cdbb

How to cite

Continuized Quasar-Convex Acceleration via an Unbiased Finite-Mixing Network Oracle — arXiv:2611.04597 — arXiv (en), https://arxiv.org/abs/2611.04597 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_394d64c1cdbb (Metraipolis archive dc_394d64c1cdbb, sha256 69129799f65a276cf16cb07b2531f89efa9c7f23263e658145a9649ddc9647f2)
BibTeX
@misc{dc394d64c1cdbb,
  title = {Continuized Quasar-Convex Acceleration via an Unbiased Finite-Mixing Network Oracle — arXiv:2611.04597},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04597},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_394d64c1cdbb; sha256 69129799f65a276cf16cb07b2531f89efa9c7f23263e658145a9649ddc9647f2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04597. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study decentralized minimization of a smooth network average that is globally quasar-convex with respect to a fixed minimizer; the node functions may be nonconvex and need not share a minimizer. A unit-rate Poisson clock drives an exactly simulable continuized process: between events the state follows a closed-form accelerated flow, and each event uses one oracle vector. One master theorem covers oracles with a predictable bias and a state-dependent variance and keeps the inverse-quadratic term $\mathcal{O}(LR_0^2/(\gamma^2T^2))$; one selected-row lemma supplies the oracle moments of three network implementations. CQA-Net keeps a common state, mixes local rows for finitely many rounds, and disseminates one uniformly selected row; its oracle is unbiased at every mixing depth, so incomplete averaging affects only the variance. A walking token removes dissemination, the shared clock, and the shared root, and an importance weight keeps it unbiased on fixed graphs. D-CQA keeps local states and mixes them; under bounded heterogeneity it needs $\widetilde{\mathcal{O}}(\sqrt{\chi}\sqrt{L}R_0/(\gamma\theta\sqrt{\varepsilon}))$ communication rounds and no dissemination. Changing graphs enter through certified operator norms. Experiments on a certified nonconvex regression on static and changing graphs compare the three implementations.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.04597 — 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 2026-11-04T21:40:34.541Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).