Lénaïc Chizat

According to our database, Lénaïc Chizat authored at least 39 papers between 2016 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow.

Lénaïc Chizat, Maria Colombo, Roberto Colombo, Xavier Fernández-Real

CoRR, May, 2026

ResNets of All Shapes and Sizes: Convergence of Training Dynamics in the Large-scale Limit.

Louis-Pierre Chaintron, Lénaïc Chizat, Javier Maass

CoRR, March, 2026

Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies.

Lénaïc Chizat, Maria Colombo, Roberto Colombo, Xavier Fernández-Real

CoRR, March, 2026

Sharper exponential convergence rates for Sinkhorn's algorithm in continuous settings.

Lénaïc Chizat, Alex Delalande, Tomas Vaskevicius

Math. Program., January, 2026

2025

Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime.

Lénaïc Chizat, Pierre Marion, Yerkin Yesbay

CoRR, October, 2025

The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagrams.

Lénaïc Chizat

CoRR, September, 2025

An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games.

Guillaume Wang, Lénaïc Chizat

Open J. Math. Optim., 2025

2024

On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks.

Sebastian Neumayer, Lénaïc Chizat, Michael Unser

J. Mach. Learn. Res., 2024

Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit.

Karl Hajjar, Lénaïc Chizat, Christophe Giraud

J. Mach. Learn. Res., 2024

Annealed Sinkhorn for Optimal Transport: convergence, regularization path and debiasing.

Lénaïc Chizat

CoRR, 2024

Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach.

Guillaume Wang, Alireza Mousavi-Hosseini, Lénaïc Chizat

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Deep linear networks for regression are implicitly regularized towards flat minima.

Pierre Marion, Lénaïc Chizat

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks.

Lénaïc Chizat, Praneeth Netrapalli

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Open problem: Convergence of single-timescale mean-field Langevin descent-ascent for two-player zero-sum games.

Guillaume Wang, Lénaïc Chizat

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Steering Deep Feature Learning with Backward Aligned Feature Updates.

Lénaïc Chizat, Praneeth Netrapalli

CoRR, 2023

Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Damped Sinkhorn Iterations.

Lénaïc Chizat, Tomas Vaskevicius

CoRR, 2023

Local Convergence of Gradient Methods for Min-Max Games under Partial Curvature.

Guillaume Wang, Lénaïc Chizat

CoRR, 2023

Doubly Regularized Entropic Wasserstein Barycenters.

Lénaïc Chizat

CoRR, 2023

Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices.

Guillaume Wang, Lénaïc Chizat

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Computational Guarantees for Doubly Entropic Wasserstein Barycenters.

Tomas Vaskevicius, Lénaïc Chizat

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Convergence Rates of Gradient Methods for Convex Optimization in the Space of Measures.

Lénaïc Chizat

Open J. Math. Optim., March, 2022

Mean-Field Langevin Dynamics : Exponential Convergence and Annealing.

Lénaïc Chizat

Trans. Mach. Learn. Res., 2022

Sparse optimization on measures with over-parameterized gradient descent.

Lénaïc Chizat

Math. Program., 2022

Infinite-width limit of deep linear neural networks.

Lénaïc Chizat, Maria Colombo, Xavier Fernández-Real, Alessio Figalli

CoRR, 2022

Symmetries in the dynamics of wide two-layer neural networks.

Karl Hajjar, Lénaïc Chizat

CoRR, 2022

Trajectory Inference via Mean-field Langevin in Path Space.

Lénaïc Chizat, Stephen Zhang, Matthieu Heitz, Geoffrey Schiebinger

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization.

Francis R. Bach, Lenaïc Chizat

CoRR, 2021

Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport.

Alexis Thibault, Lénaïc Chizat, Charles Dossal, Nicolas Papadakis

Algorithms, 2021

2020

Statistical and Topological Properties of Sliced Probability Divergences.

Kimia Nadjahi, Alain Durmus, Lénaïc Chizat, Soheil Kolouri, Shahin Shahrampour, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Faster Wasserstein Distance Estimation with the Sinkhorn Divergence.

Lénaïc Chizat, Pierre Roussillon, Flavien Léger, François-Xavier Vialard, Gabriel Peyré

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss.

Lénaïc Chizat, Francis R. Bach

Proceedings of the Conference on Learning Theory, 2020

2019

HexaShrink, an exact scalable framework for hexahedral meshes with attributes and discontinuities: multiresolution rendering and storage of geoscience models.

Jean-Luc Peyrot, Laurent Duval, Frédéric Payan, Lauriane Bouard, Lénaïc Chizat, Sébastien Schneider, Marc Antonini

CoRR, 2019

On Lazy Training in Differentiable Programming.

Lénaïc Chizat, Edouard Oyallon, Francis R. Bach

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Sample Complexity of Sinkhorn Divergences.

Aude Genevay, Lénaïc Chizat, Francis R. Bach, Marco Cuturi, Gabriel Peyré

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Scaling algorithms for unbalanced optimal transport problems.

Lenaïc Chizat, Gabriel Peyré, Bernhard Schmitzer, François-Xavier Vialard

Math. Comput., 2018

An Interpolating Distance Between Optimal Transport and Fisher-Rao Metrics.

Lenaïc Chizat, Gabriel Peyré, Bernhard Schmitzer, François-Xavier Vialard

Found. Comput. Math., 2018

A Note on Lazy Training in Supervised Differentiable Programming.

Lénaïc Chizat, Francis R. Bach

CoRR, 2018

On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport.

Lénaïc Chizat, Francis R. Bach

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2016

Quantum Optimal Transport for Tensor Field Processing.

Gabriel Peyré, Lenaïc Chizat, François-Xavier Vialard, Justin Solomon

CoRR, 2016