Publications

Mathieu Even, Scott Pesme, Suriya Gunasekar, Nicolas Flammarion (2023). Implicit Regularisation, Large Stepsizes and Edge of Stability for (S)GD over Diagonal Linear Networks. Neural Information Processing Systems (NeurIPS), 2023.

Mathieu Even (2023). Stochastic Gradient Descent under Markov Chain Sampling Schemes. International conference on Machine Learning, 2023.

Edwige Cyffers, Mathieu Even, Aurélien Bellet, Laurent Massoulié (2022). Muffliato Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging. Neural Information Processing Systems (NeurIPS), 2021.

Konstantin Mischenko, Francis Bach, Mathieu Even, Blake Woodworth (2022). Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays. Neural Information Processing Systems (NeurIPS), 2022.

Mathieu Even, Laurent Massoulié, Kevin Scaman (2022). On Sample Optimality in Personalized Federated and Collaborative Learning. Neural Information Processing Systems (NeurIPS), 2022.

Mathieu Even, Raphaël Berthier, Francis Bach, Nicolas Flamarrion, Pierre Gaillard, Hadrien Hendrikx, Laurent Massoulié, Adrien Taylor (2021). A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip. NeurIPS2021 Outstanding Paper Award.

Mathieu Even, Hadrien Hendrikx, Laurent Massoulié (2021). Decentralized Optimization with Heterogeneous Delays: a Continuous-Time Approach.

RA Dragomir, Mathieu Even, Hadrien Hendrikx (2021). Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction. ICML2021.

Mathieu Even, Laurent Massoulié (2021). Concentration of Non-Isotropic Random Tensors with Applications to Learning and Empirical Risk Minimization. COLT2021.

Mathieu Even, Hadrien Hendrikx, Laurent Massoulié (2021). Asynchrony and Acceleration in Gossip Algorithms.