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

Avetik Karagulyan, Peter Richtárik

Keywords: Federated Sampling, Langevin Sampling

Abstract:

Federated sampling algorithms have recently
gained great popularity in the community of machine learning and statistics. This paper proposes
a new federated sampling algorithm 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 primal, dual, and bidirectional compressors. We analyze the proposed methods under Log-Sobolev inequality and provide non-asymptotic
convergence guarantees. Simple experimental results support our theoretical findings.

Readers: auai.org/UAI/2025/Conference, auai.org/UAI/2025/Conference/Area_Chairs, auai.org/UAI/2025/Conference/Reviewers, auai.org/UAI/2025/Conference/Submission786/Authors, auai.org/UAI/2025/Conference/Submission786/Reproducibility_Reviewers

Submission Number: 786