b'Joan Bruna'

research

∙ 07/28/2023

On Single Index Models beyond Gaussian Data

Sparse high-dimensional functions have arisen as a rich framework to stu...

0 Joan Bruna, et al. ∙

research

∙ 07/04/2023

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Graph neural networks (GNNs) have become increasingly popular for classi...

0 Vignesh Kothapalli, et al. ∙

research

∙ 05/31/2023

Conditionally Strongly Log-Concave Generative Models

There is a growing gap between the impressive results of deep image gene...

0 Florentin Guth, et al. ∙

research

∙ 05/26/2023

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

In recent years, domains such as natural language processing and image r...

0 David Brandfonbrener, et al. ∙

research

∙ 10/28/2022

A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks

To understand the training dynamics of neural networks (NNs), prior stud...

0 Zhengdao Chen, et al. ∙

research

∙ 10/27/2022

Learning Single-Index Models with Shallow Neural Networks

Single-index models are a class of functions given by an unknown univari...

0 Alberto Bietti, et al. ∙

research

∙ 08/05/2022

Towards Antisymmetric Neural Ansatz Separation

We study separations between two fundamental models (or Ansätze) of anti...

0 Aaron Zweig, et al. ∙

research

∙ 07/06/2022

On Non-Linear operators for Geometric Deep Learning

This work studies operators mapping vector and scalar fields defined ove...

0 Grégoire Sergeant-Perthuis, et al. ∙

research

∙ 06/08/2022

On Gradient Descent Convergence beyond the Edge of Stability

Gradient Descent (GD) is a powerful workhorse of modern machine learning...

0 Lei Chen, et al. ∙

research

∙ 06/02/2022

Exponential Separations in Symmetric Neural Networks

In this work we demonstrate a novel separation between symmetric neural ...

0 Aaron Zweig, et al. ∙

research

∙ 06/02/2022

When does return-conditioned supervised learning work for offline reinforcement learning?

Several recent works have proposed a class of algorithms for the offline...

0 David Brandfonbrener, et al. ∙

research

∙ 04/22/2022

On Feature Learning in Neural Networks with Global Convergence Guarantees

We study the optimization of wide neural networks (NNs) via gradient flo...

5 Zhengdao Chen, et al. ∙

research

∙ 03/02/2022

Neural Galerkin Scheme with Active Learning for High-Dimensional Evolution Equations

Machine learning methods have been shown to give accurate predictions in...

9 Joan Bruna, et al. ∙

research

∙ 02/16/2022

Extended Unconstrained Features Model for Exploring Deep Neural Collapse

The modern strategy for training deep neural networks for classification...

0 Tom Tirer, et al. ∙

research

∙ 02/14/2022

Simultaneous Transport Evolution for Minimax Equilibria on Measures

Min-max optimization problems arise in several key machine learning setu...

0 Carles Domingo Enrich, et al. ∙

research

∙ 12/07/2021

Lattice-Based Methods Surpass Sum-of-Squares in Clustering

Clustering is a fundamental primitive in unsupervised learning which giv...

0 Ilias Zadik, et al. ∙

research

∙ 12/02/2021

Quantile Filtered Imitation Learning

We introduce quantile filtered imitation learning (QFIL), a novel policy...

0 David Brandfonbrener, et al. ∙

research

∙ 11/26/2021

Neural Fields as Learnable Kernels for 3D Reconstruction

We present Neural Kernel Fields: a novel method for reconstructing impli...

27 Francis Williams, et al. ∙

research

∙ 11/25/2021

Multi-fidelity Stability for Graph Representation Learning

In the problem of structured prediction with graph representation learni...

0 Yihan He, et al. ∙

research

∙ 10/12/2021

A Rate-Distortion Framework for Explaining Black-box Model Decisions

We present the Rate-Distortion Explanation (RDE) framework, a mathematic...

0 Stefan Kolek, et al. ∙

research

∙ 10/07/2021

Cartoon Explanations of Image Classifiers

We present CartoonX (Cartoon Explanation), a novel model-agnostic explan...

0 Stefan Kolek, et al. ∙

research

∙ 07/11/2021

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

Energy-based models (EBMs) are generative models that are usually traine...

6 Carles Domingo Enrich, et al. ∙

research

∙ 06/20/2021

On the Cryptographic Hardness of Learning Single Periodic Neurons

We show a simple reduction which demonstrates the cryptographic hardness...

0 Min Jae Song, et al. ∙

research

∙ 06/16/2021

Offline RL Without Off-Policy Evaluation

Most prior approaches to offline reinforcement learning (RL) have taken ...

0 David Brandfonbrener, et al. ∙

research

∙ 06/14/2021

On the Sample Complexity of Learning with Geometric Stability

Many supervised learning problems involve high-dimensional data such as ...

0 Alberto Bietti, et al. ∙

research

∙ 04/27/2021

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

The last decade has witnessed an experimental revolution in data science...

288 Michael M. Bronstein, et al. ∙

research

∙ 04/15/2021

On Energy-Based Models with Overparametrized Shallow Neural Networks

Energy-based models (EBMs) are a simple yet powerful framework for gener...

15 Carles Domingo Enrich, et al. ∙

research

∙ 03/10/2021

Symmetry Breaking in Symmetric Tensor Decomposition

In this note, we consider the optimization problem associated with compu...

12 Yossi Arjevani, et al. ∙

research

∙ 02/02/2021

Depth separation beyond radial functions

High-dimensional depth separation results for neural networks show that ...

0 Luca Venturi, et al. ∙

research

∙ 02/01/2021

Self-Supervised Equivariant Scene Synthesis from Video

We propose a self-supervised framework to learn scene representations fr...

8 Cinjon Resnick, et al. ∙

research

∙ 11/11/2020

Learned Equivariant Rendering without Transformation Supervision

We propose a self-supervised framework to learn scene representations fr...

4 Cinjon Resnick, et al. ∙

research

∙ 10/28/2020

On Graph Neural Networks versus Graph-Augmented MLPs

From the perspective of expressive power, this work compares multi-layer...

0 Lei Chen, et al. ∙

research

∙ 09/21/2020

Kernel-Based Smoothness Analysis of Residual Networks

A major factor in the success of deep neural networks is the use of soph...

21 Tom Tirer, et al. ∙

research

∙ 08/21/2020

A Dynamical Central Limit Theorem for Shallow Neural Networks

Recent theoretical work has characterized the dynamics of wide shallow n...

8 Zhengdao Chen, et al. ∙

research

∙ 08/16/2020

A Functional Perspective on Learning Symmetric Functions with Neural Networks

Symmetric functions, which take as input an unordered, fixed-size set, a...

13 Aaron Zweig, et al. ∙

research

∙ 07/28/2020

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...

0 Donsub Rim, et al. ∙

research

∙ 07/01/2020

In-Distribution Interpretability for Challenging Modalities

It is widely recognized that the predictions of deep neural networks are...

16 Cosmas Heiß, et al. ∙

research

∙ 06/27/2020

Overfitting and Optimization in Offline Policy Learning

We consider the task of policy learning from an offline dataset generate...

11 David Brandfonbrener, et al. ∙

research

∙ 06/24/2020

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

We present Neural Splines, a technique for 3D surface reconstruction tha...

6 Francis Williams, et al. ∙

research

∙ 06/18/2020

On Sparsity in Overparametrised Shallow ReLU Networks

The analysis of neural network training beyond their linearization regim...

0 Jaume de Dios, et al. ∙

research

∙ 06/11/2020

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

We introduce a framework for designing primal methods under the decentra...

0 Yossi Arjevani, et al. ∙

research

∙ 05/19/2020

Continuous LWE

We introduce a continuous analogue of the Learning with Errors (LWE) pro...

0 Joan Bruna, et al. ∙

research

∙ 03/02/2020

A Permutation-Equivariant Neural Network Architecture For Auction Design

Designing an incentive compatible auction that maximizes expected revenu...

23 Jad Rahme, et al. ∙

research

∙ 02/27/2020

Provably Efficient Third-Person Imitation from Offline Observation

Domain adaptation in imitation learning represents an essential step tow...

4 Aaron Zweig, et al. ∙

research

∙ 02/14/2020

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

Finding Nash equilibria in two-player zero-sum continuous games is a cen...

5 Carles Domingo Enrich, et al. ∙

research

∙ 02/10/2020

Can graph neural networks count substructures?

The ability to detect and count certain substructures in graphs is impor...

37 Zhengdao Chen, et al. ∙

research

∙ 11/30/2019

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

Self-supervised research improved greatly over the past half decade, wit...

12 Cinjon Resnick, et al. ∙

research

∙ 10/21/2019

Stability of Graph Neural Networks to Relative Perturbations

Graph neural networks (GNNs), consisting of a cascade of layers applying...

24 Fernando Gama, et al. ∙

research

∙ 10/03/2019

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

The critical locus of the loss function of a neural network is determine...

7 Matthew Trager, et al. ∙

research

∙ 06/18/2019

Gradient Dynamics of Shallow Univariate ReLU Networks

We present a theoretical and empirical study of the gradient dynamics of...

3 Francis Williams, et al. ∙

Joan Bruna

Featured Co-authors