← Authors

Lénaïc Chizat

15 papers · 2018–2024 · 4 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🏃 Academic Marathon (6) 🐝 Cross-Pollinator (9) 🗺️ Taxonomy Completionist (20) 🌍 Conference Polyglot (4) 💎 Century Club (15) 🗃️ Keyword Collector (74) ⚡ Prolific Year (6)

Conferences

NIPS (10) COLT (2) JMLR (2) AISTATS (1)

Top co-authors

Francis Bach (4) Guillaume Wang (3) Gabriel Peyré (2) Marco Cuturi (1) Shahin Shahrampour (1) Sebastian Neumayer (1) Pierre Roussillon (1) Michael Unser (1) Kimia Nadjahi (1) Stephen Zhang (1)

Keywords

gradient descent (5) optimal transport (4) neural network (3) neural network optimization (2) entropic regularization (2) convex optimization (2) sinkhorn divergence (2) zero-sum game (2) feature learning (2) wasserstein distance (2) gradient-based method (1) nash equilibrium (1) neural network training (1) neural tangent kernel (1) sample complexity (1) bilevel optimization (1) global convergence (1) hyperparameter tuning (1) logistic loss (1) trajectory inference (1)

Papers

Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit JMLR 2024
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach NIPS 2024
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks NIPS 2024
Deep linear networks for regression are implicitly regularized towards flat minima NIPS 2024
Open problem: Convergence of single-timescale mean-field Langevin descent-ascent for two-player zero-sum games COLT 2024
On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks JMLR 2024
Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices NIPS 2023
Computational Guarantees for Doubly Entropic Wasserstein Barycenters NIPS 2023
Trajectory Inference via Mean-field Langevin in Path Space NIPS 2022
Faster Wasserstein Distance Estimation with the Sinkhorn Divergence NIPS 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 NIPS 2020
Sample Complexity of Sinkhorn Divergences AISTATS 2019
On Lazy Training in Differentiable Programming NIPS 2019
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport NIPS 2018