Metraipolis › archive › dc_f9db80342e5c

A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization — arXiv:2610.20075

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20075
License (as archived)
CC0-1.0
Archived
2026-10-15T14:19:30.127Z
SHA-256 of the archived text
f7ecbcdcba5693bcafed5107f052d97f24ed7c0880b94bfd5195dc4c34350552
Stable URL of this page
https://metraipolis.com/documento/dc_f9db80342e5c

How to cite

A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization — arXiv:2610.20075 — arXiv (en), https://arxiv.org/abs/2610.20075 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f9db80342e5c (Metraipolis archive dc_f9db80342e5c, sha256 f7ecbcdcba5693bcafed5107f052d97f24ed7c0880b94bfd5195dc4c34350552)
BibTeX
@misc{dcf9db80342e5c,
  title = {A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization — arXiv:2610.20075},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20075},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f9db80342e5c; sha256 f7ecbcdcba5693bcafed5107f052d97f24ed7c0880b94bfd5195dc4c34350552},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20075. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated learning over decentralized networks inherently trades off the suppression of local finite-sample noise through collaboration against the bias that collaboration introduces between heterogeneous nodes. We study this tension by performing a large-dimensional analysis of Generalized Total Variation Minimization with least-squares models. Using tools from random matrix theory, we show that Lipschitz observations of the global GTVMin solution concentrate in large dimensions, universally for any underlying network structure. We provide exact analytic expressions for the asymptotically precise performance under both i.i.d. and non-i.i.d. Gaussian mixture distributions on a fixed network. For the latter, these expressions quantify how regularization balances local adaptation against collaboration. Our theoretical results are confirmed by experiments on synthetic and real-world data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.20075 — 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 2026-10-15T13:53:35.695Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).