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

Avetik Karagulyan, Peter Richtárik
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:1965-1989, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-karagulyan25a, title = {ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression}, author = {Karagulyan, Avetik and Richt\'{a}rik, Peter}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {1965--1989}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/karagulyan25a/karagulyan25a.pdf}, url = {https://proceedings.mlr.press/v286/karagulyan25a.html}, 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.} }
Endnote
%0 Conference Paper %T ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression %A Avetik Karagulyan %A Peter Richtárik %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-karagulyan25a %I PMLR %P 1965--1989 %U https://proceedings.mlr.press/v286/karagulyan25a.html %V 286 %X 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.
APA
Karagulyan, A. & Richtárik, P.. (2025). ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:1965-1989 Available from https://proceedings.mlr.press/v286/karagulyan25a.html.

Related Material