5.6k citations · 17.4k across the 77 of their papers we have counts for
80 papers
On Single Index Models beyond Gaussian Data
Joan Bruna, Loucas Pillaud-Vivien, Aaron Zweig
Sparse high-dimensional functions have arisen as a rich framework to study the behavior of gradient-descent methods using shallow neural networks, showcasing their ability to perfo…
A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
Vignesh Kothapalli, Tom Tirer, Joan Bruna
Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in…
Conditionally Strongly Log-Concave Generative Models
Florentin Guth, Etienne Lempereur, Joan Bruna +1
There is a growing gap between the impressive results of deep image generative models and classical algorithms that offer theoretical guarantees. The former suffer from mode collap…
Learning Single-Index Models with Shallow Neural Networks
Alberto Bietti, Joan Bruna, Clayton Sanford +1
Single-index models are a class of functions given by an unknown univariate ``link'' function applied to an unknown one-dimensional projection of the input. These models are partic…
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna
To understand the training dynamics of neural networks, prior studies have considered the mean-field limit of two-layer neural networks as the width tends to infinity, establishing…
Towards Antisymmetric Neural Ansatz Separation
Aaron Zweig, Joan Bruna
We study separations between two fundamental models (or \emph{Ansätze}) of antisymmetric functions, that is, functions of the form $f(x_{σ(1)}, \ldots, x_{σ(N)}) = \text{sign}(…