3 citations · 6 across the 9 of their papers we have counts for
9 papers
Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow
Lénaïc Chizat, Maria Colombo, Roberto Colombo +1
Stein Variational Gradient Descent (SVGD) is a deterministic interacting-particle method for sampling from a target probability measure given access to its score function. In the m…
Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies
Lénaïc Chizat, Maria Colombo, Roberto Colombo +1
We study the quantitative convergence of Wasserstein gradient flows of Kernel Mean Discrepancy (KMD) (also known as Maximum Mean Discrepancy (MMD)) functionals. Our setting covers…
Deep linear networks for regression are implicitly regularized towards flat minima
Pierre Marion, Lénaïc Chizat
The largest eigenvalue of the Hessian, or sharpness, of neural networks is a key quantity to understand their optimization dynamics. In this paper, we study the sharpness of deep l…
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
Lénaïc Chizat, Praneeth Netrapalli
Deep learning succeeds by doing hierarchical feature learning, yet tuning hyper-parameters (HP) such as initialization scales, learning rates etc., only give indirect control over…
On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks
Sebastian Neumayer, Lénaïc Chizat, Michael Unser
In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this pap…
Displacement smoothness of entropic optimal transport
Guillaume Carlier, Lénaïc Chizat, Maxime Laborde
The function that maps a family of probability measures to the solution of the dual entropic optimal transport problem is known as the Schrödinger map. We prove that when the cost…
Mean-Field Langevin Dynamics: Exponential Convergence and Annealing
Lénaïc Chizat
Noisy particle gradient descent (NPGD) is an algorithm to minimize convex functions over the space of measures that include an entropy term. In the many-particle limit, this algori…
Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit
Karl Hajjar, Lénaïc Chizat, Christophe Giraud
To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, t…
Convergence Rates of Gradient Methods for Convex Optimization in the Space of Measures
Lénaïc Chizat
We study the convergence rate of Bregman gradient methods for convex optimization in the space of measures on a -dimensional manifold. Under basic regularity assumptions, we sho…