Lénaïc Chizat
15 papers · 2018–2024 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (23)
🧭
Keyword Pioneer
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(72)
Venues
Top co-authors
Research topics
Machine Learning
(13)
Optimization & Theory · Machine Learning
(13)
Mathematics & Optimization
(9)
Optimization
(7)
Deep Learning
(6)
Mathematics
(6)
Architectures
(4)
Optimization & Theory · Deep Learning
(4)
Artificial Intelligence
(2)
Techniques
(2)
Bayesian & Probabilistic
(1)
Core AI
(1)
Learning Paradigms
(1)
Probability
(1)
Keywords
gradient descent
(5)
optimal transport
(4)
neural network
(3)
convex optimization
(2)
wasserstein distance
(2)
entropic regularization
(2)
mean-field langevin dynamics
(2)
wasserstein gradient flow
(2)
zero-sum game
(2)
infinite-width limit
(2)
feature learning
(2)
neural network optimization
(2)
nash equilibrium
(2)
sinkhorn divergence
(2)
neural network training
(1)
sample complexity
(1)
neural tangent kernel
(1)
global convergence
(1)
hyperparameter tuning
(1)
mean field theory
(1)
Papers
Deep linear networks for regression are implicitly regularized towards flat minima
NeurIPS 2024
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
NeurIPS 2024
On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks
JMLR 2024
Open problem: Convergence of single-timescale mean-field Langevin descent-ascent for two-player zero-sum games
COLT 2024
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
NeurIPS 2024
Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit
JMLR 2024
Computational Guarantees for Doubly Entropic Wasserstein Barycenters
NeurIPS 2023
Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices
NeurIPS 2023
Trajectory Inference via Mean-field Langevin in Path Space
NeurIPS 2022
Faster Wasserstein Distance Estimation with the Sinkhorn Divergence
NeurIPS 2020
Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss
COLT 2020
Statistical and Topological Properties of Sliced Probability Divergences
NeurIPS 2020
On Lazy Training in Differentiable Programming
NeurIPS 2019
Sample Complexity of Sinkhorn Divergences
AISTATS 2019
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
NeurIPS 2018