Joan Bruna

is this you? claim profile

∙ 0 followers
Facebook ∙ NYU college ∙ berkeley college

Assistant Professor at Courant Institute, New York University

Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networks

Energy-based models (EBMs) are generative models that are usually traine...
07/11/2021 ∙ by Carles Domingo Enrich, et al. ∙ 6 ∙ share

read it
On the Cryptographic Hardness of Learning Single Periodic Neurons

We show a simple reduction which demonstrates the cryptographic hardness...
06/20/2021 ∙ by Min Jae Song, et al. ∙ 0 ∙ share

read it
Offline RL Without Off-Policy Evaluation

Most prior approaches to offline reinforcement learning (RL) have taken ...
06/16/2021 ∙ by David Brandfonbrener, et al. ∙ 0 ∙ share

read it
On the Sample Complexity of Learning with Geometric Stability

Many supervised learning problems involve high-dimensional data such as ...
06/14/2021 ∙ by Alberto Bietti, et al. ∙ 0 ∙ share

read it
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

The last decade has witnessed an experimental revolution in data science...
04/27/2021 ∙ by Michael M. Bronstein, et al. ∙ 288 ∙ share

read it
On Energy-Based Models with Overparametrized Shallow Neural Networks

Energy-based models (EBMs) are a simple yet powerful framework for gener...
04/15/2021 ∙ by Carles Domingo Enrich, et al. ∙ 15 ∙ share

read it
Symmetry Breaking in Symmetric Tensor Decomposition

In this note, we consider the optimization problem associated with compu...
03/10/2021 ∙ by Yossi Arjevani, et al. ∙ 12 ∙ share

read it
Depth separation beyond radial functions

High-dimensional depth separation results for neural networks show that ...
02/02/2021 ∙ by Luca Venturi, et al. ∙ 0 ∙ share

read it
Self-Supervised Equivariant Scene Synthesis from Video

We propose a self-supervised framework to learn scene representations fr...
02/01/2021 ∙ by Cinjon Resnick, et al. ∙ 8 ∙ share

read it
Learned Equivariant Rendering without Transformation Supervision

We propose a self-supervised framework to learn scene representations fr...
11/11/2020 ∙ by Cinjon Resnick, et al. ∙ 4 ∙ share

read it
On Graph Neural Networks versus Graph-Augmented MLPs

From the perspective of expressive power, this work compares multi-layer...
10/28/2020 ∙ by Lei Chen, et al. ∙ 0 ∙ share

read it
Kernel-Based Smoothness Analysis of Residual Networks

A major factor in the success of deep neural networks is the use of soph...
09/21/2020 ∙ by Tom Tirer, et al. ∙ 21 ∙ share

read it
A Dynamical Central Limit Theorem for Shallow Neural Networks

Recent theoretical work has characterized the dynamics of wide shallow n...
08/21/2020 ∙ by Zhengdao Chen, et al. ∙ 8 ∙ share

read it
A Functional Perspective on Learning Symmetric Functions with Neural Networks

Symmetric functions, which take as input an unordered, fixed-size set, a...
08/16/2020 ∙ by Aaron Zweig, et al. ∙ 13 ∙ share

read it
Depth separation for reduced deep networks in nonlinear model reduction: Distilling shock waves in nonlinear hyperbolic problems

Classical reduced models are low-rank approximations using a fixed basis...
07/28/2020 ∙ by Donsub Rim, et al. ∙ 0 ∙ share

read it
In-Distribution Interpretability for Challenging Modalities

It is widely recognized that the predictions of deep neural networks are...
07/01/2020 ∙ by Cosmas Heiß, et al. ∙ 16 ∙ share

read it
Overfitting and Optimization in Offline Policy Learning

We consider the task of policy learning from an offline dataset generate...
06/27/2020 ∙ by David Brandfonbrener, et al. ∙ 11 ∙ share

read it
Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networks

We present Neural Splines, a technique for 3D surface reconstruction tha...
06/24/2020 ∙ by Francis Williams, et al. ∙ 6 ∙ share

read it
On Sparsity in Overparametrised Shallow ReLU Networks

The analysis of neural network training beyond their linearization regim...
06/18/2020 ∙ by Jaume de Dios, et al. ∙ 0 ∙ share

read it
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

We introduce a framework for designing primal methods under the decentra...
06/11/2020 ∙ by Yossi Arjevani, et al. ∙ 0 ∙ share

read it
Continuous LWE

We introduce a continuous analogue of the Learning with Errors (LWE) pro...
05/19/2020 ∙ by Joan Bruna, et al. ∙ 0 ∙ share

read it
A Permutation-Equivariant Neural Network Architecture For Auction Design

Designing an incentive compatible auction that maximizes expected revenu...
03/02/2020 ∙ by Jad Rahme, et al. ∙ 23 ∙ share

read it
Provably Efficient Third-Person Imitation from Offline Observation

Domain adaptation in imitation learning represents an essential step tow...
02/27/2020 ∙ by Aaron Zweig, et al. ∙ 4 ∙ share

read it
A mean-field analysis of two-player zero-sum games

Finding Nash equilibria in two-player zero-sum continuous games is a cen...
02/14/2020 ∙ by Carles Domingo Enrich, et al. ∙ 5 ∙ share

read it
Can graph neural networks count substructures?

The ability to detect and count certain substructures in graphs is impor...
02/10/2020 ∙ by Zhengdao Chen, et al. ∙ 37 ∙ share

read it
Probing the State of the Art: A Critical Look at Visual Representation Evaluation

Self-supervised research improved greatly over the past half decade, wit...
11/30/2019 ∙ by Cinjon Resnick, et al. ∙ 12 ∙ share

read it
Stability of Graph Neural Networks to Relative Perturbations

Graph neural networks (GNNs), consisting of a cascade of layers applying...
10/21/2019 ∙ by Fernando Gama, et al. ∙ 24 ∙ share

read it
Pure and Spurious Critical Points: a Geometric Study of Linear Networks

The critical locus of the loss function of a neural network is determine...
10/03/2019 ∙ by Matthew Trager, et al. ∙ 7 ∙ share

read it
Gradient Dynamics of Shallow Univariate ReLU Networks

We present a theoretical and empirical study of the gradient dynamics of...
06/18/2019 ∙ by Francis Williams, et al. ∙ 3 ∙ share

read it
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias

Despite the phenomenal success of deep neural networks in a broad range ...
06/16/2019 ∙ by Stéphane d'Ascoli, et al. ∙ 0 ∙ share

read it
Stability of Graph Scattering Transforms

Scattering transforms are non-trainable deep convolutional architectures...
06/11/2019 ∙ by Fernando Gama, et al. ∙ 4 ∙ share

read it
On the equivalence between graph isomorphism testing and function approximation with GNNs

Graph neural networks (GNNs) have achieved lots of success on graph-stru...
05/29/2019 ∙ by Zhengdao Chen, et al. ∙ 2 ∙ share

read it
Extra-gradient with player sampling for provable fast convergence in n-player games

Data-driven model training is increasingly relying on finding Nash equil...
05/29/2019 ∙ by Samy Jelassi, et al. ∙ 0 ∙ share

read it
On the Expressive Power of Deep Polynomial Neural Networks

We study deep neural networks with polynomial activations, particularly ...
05/29/2019 ∙ by Joe Kileel, et al. ∙ 5 ∙ share

read it
On the Expected Dynamics of Nonlinear TD Learning

While there are convergence guarantees for temporal difference (TD) lear...
05/29/2019 ∙ by David Brandfonbrener, et al. ∙ 8 ∙ share

read it
Stability Properties of Graph Neural Networks

Data stemming from networks exhibit an irregular support, whereby each d...
05/11/2019 ∙ by Fernando Gama, et al. ∙ 22 ∙ share

read it
Advancing GraphSAGE with A Data-Driven Node Sampling

As an efficient and scalable graph neural network, GraphSAGE has enabled...
04/29/2019 ∙ by Jihun Oh, et al. ∙ 30 ∙ share

read it
Global convergence of neuron birth-death dynamics

Neural networks with a large number of parameters admit a mean-field des...
02/05/2019 ∙ by Grant Rotskoff, et al. ∙ 4 ∙ share

read it
Kymatio: Scattering Transforms in Python

The wavelet scattering transform is an invariant signal representation s...
12/28/2018 ∙ by Mathieu Andreux, et al. ∙ 12 ∙ share

read it
Deep Geometric Prior for Surface Reconstruction

The reconstruction of a discrete surface from a point cloud is a fundame...
11/27/2018 ∙ by Francis Williams, et al. ∙ 8 ∙ share

read it
Pommerman: A Multi-Agent Playground

We present Pommerman, a multi-agent environment based on the classic con...
09/19/2018 ∙ by Cinjon Resnick, et al. ∙ 0 ∙ share

read it
Graph Neural Networks for IceCube Signal Classification

Tasks involving the analysis of geometric (graph- and manifold-structure...
09/17/2018 ∙ by Nicholas Choma, et al. ∙ 2 ∙ share

read it
Planning with Arithmetic and Geometric Attributes

A desirable property of an intelligent agent is its ability to understan...
09/06/2018 ∙ by David Folqué, et al. ∙ 10 ∙ share

read it
Backplay: "Man muss immer umkehren"

A long-standing problem in model free reinforcement learning (RL) is tha...
07/18/2018 ∙ by Cinjon Resnick, et al. ∙ 2 ∙ share

read it
Diffusion Scattering Transforms on Graphs

Stability is a key aspect of data analysis. In many applications, the na...
06/22/2018 ∙ by Fernando Gama, et al. ∙ 0 ∙ share

read it
Neural Networks with Finite Intrinsic Dimension have no Spurious Valleys

Neural networks provide a rich class of high-dimensional, non-convex opt...
02/18/2018 ∙ by Luca Venturi, et al. ∙ 0 ∙ share

read it
Multiscale Sparse Microcanonical Models

We study density estimation of stationary processes defined over an infi...
01/06/2018 ∙ by Joan Bruna, et al. ∙ 0 ∙ share

read it
Mathematics of Deep Learning

Recently there has been a dramatic increase in the performance of recogn...
12/13/2017 ∙ by Rene Vidal, et al. ∙ 0 ∙ share

read it
Few-Shot Learning with Graph Neural Networks

We propose to study the problem of few-shot learning with the prism of i...
11/10/2017 ∙ by Victor Garcia, et al. ∙ 0 ∙ share

read it
A Note on Learning Algorithms for Quadratic Assignment with Graph Neural Networks

Many inverse problems are formulated as optimization problems over certa...
06/22/2017 ∙ by Alex Nowak, et al. ∙ 0 ∙ share

read it

Joan Bruna

Featured Co-authors