Pré-Publication, Document De Travail Année : 2023

ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression

Résumé

Federated sampling algorithms have recently gained great popularity in the community of machine learning and statistics. This paper studies variants of such algorithms called Error Feedback Langevin algorithms (ELF). In particular, we analyze the combinations of EF21 and EF21-P with the federated Langevin Monte-Carlo. We propose three algorithms: P-ELF, D-ELF, and B-ELF that use, respectively, primal, dual, and bidirectional compressors. We analyze the proposed methods under Log-Sobolev inequality and provide non-asymptotic convergence guarantees.

Dates et versions

hal-04901378 , version 1 (20-01-2025)

Identifiants

Citer

Avetik Karagulyan, Peter Richtárik. ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression. 2023. ⟨hal-04901378⟩
26 Consultations
0 Téléchargements

Altmetric

Partager

  • More