Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Aymeric Dieuleveut

Aymeric Dieuleveut

SIERRA, LIENS

QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning


Jun 01, 2021
Maxime Vono, Vincent Plassier, Alain Durmus, Aymeric Dieuleveut, Eric Moulines


  Access Paper or Ask Questions

Preserved central model for faster bidirectional compression in distributed settings


Feb 24, 2021
Constantin Philippenko, Aymeric Dieuleveut


  Access Paper or Ask Questions

On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent


Jul 01, 2020
Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion


  Access Paper or Ask Questions

Artemis: tight convergence guarantees for bidirectional compression in Federated Learning


Jun 25, 2020
Constantin Philippenko, Aymeric Dieuleveut

* 46 pages, 3 theorems 

  Access Paper or Ask Questions

Communication trade-offs for synchronized distributed SGD with large step size


Apr 25, 2019
Kumar Kshitij Patel, Aymeric Dieuleveut


  Access Paper or Ask Questions

Unsupervised Scalable Representation Learning for Multivariate Time Series


Jan 30, 2019
Jean-Yves Franceschi, Aymeric Dieuleveut, Martin Jaggi


  Access Paper or Ask Questions

Is Wasserstein all you need?


Oct 18, 2018
Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi


  Access Paper or Ask Questions

Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains


Apr 11, 2018
Aymeric Dieuleveut, Alain Durmus, Francis Bach


  Access Paper or Ask Questions

Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression


Feb 24, 2016
Aymeric Dieuleveut, Nicolas Flammarion, Francis Bach


  Access Paper or Ask Questions