Search Results for author: Joan Bruna

Found 102 papers, 41 papers with code

Extra-gradient with player sampling for faster convergence in n-player games

no code implementations ICML 2020 Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna

Data-driven modeling increasingly requires to find a Nash equilibrium in multi-player games, e. g. when training GANs.

On Single Index Models beyond Gaussian Data

no code implementations28 Jul 2023 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 perform feature learning beyond linear models.

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

1 code implementation4 Jul 2023 Vignesh Kothapalli, Tom Tirer, Joan Bruna

We start with an empirical study that shows that a decrease in within-class variability is also prevalent in the node-wise classification setting, however, not to the extent observed in the instance-wise case.

Classification Community Detection +2

Conditionally Strongly Log-Concave Generative Models

1 code implementation31 May 2023 Florentin Guth, Etienne Lempereur, Joan Bruna, Stéphane Mallat

There is a growing gap between the impressive results of deep image generative models and classical algorithms that offer theoretical guarantees.


Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

1 code implementation26 May 2023 David Brandfonbrener, Ofir Nachum, Joan Bruna

In recent years, domains such as natural language processing and image recognition have popularized the paradigm of using large datasets to pretrain representations that can be effectively transferred to downstream tasks.

Imitation Learning

Data-driven multiscale modeling of subgrid parameterizations in climate models

no code implementations24 Mar 2023 Karl Otness, Laure Zanna, Joan Bruna

Subgrid parameterizations, which represent physical processes occurring below the resolution of current climate models, are an important component in producing accurate, long-term predictions for the climate.

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

no code implementations28 Oct 2022 Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna

To understand the training dynamics of neural networks (NNs), prior studies have considered the infinite-width mean-field (MF) limit of two-layer NN, establishing theoretical guarantees of its convergence under gradient flow training as well as its approximation and generalization capabilities.

Learning Single-Index Models with Shallow Neural Networks

no code implementations27 Oct 2022 Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song

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.

Towards Antisymmetric Neural Ansatz Separation

no code implementations5 Aug 2022 Aaron Zweig, Joan Bruna

We study separations between two fundamental models (or \emph{Ans\"atze}) of antisymmetric functions, that is, functions $f$ of the form $f(x_{\sigma(1)}, \ldots, x_{\sigma(N)}) = \text{sign}(\sigma)f(x_1, \ldots, x_N)$, where $\sigma$ is any permutation.

On Non-Linear operators for Geometric Deep Learning

no code implementations6 Jul 2022 Grégoire Sergeant-Perthuis, Jakob Maier, Joan Bruna, Edouard Oyallon

In the context of Neural Networks defined over $\mathcal{M}$, it indicates that point-wise non-linear operators are the only universal family that commutes with any group of symmetries, and justifies their systematic use in combination with dedicated linear operators commuting with specific symmetries.

Beyond the Edge of Stability via Two-step Gradient Updates

no code implementations8 Jun 2022 Lei Chen, Joan Bruna

Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces.

Exponential Separations in Symmetric Neural Networks

no code implementations2 Jun 2022 Aaron Zweig, Joan Bruna

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

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

1 code implementation2 Jun 2022 David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna

Several recent works have proposed a class of algorithms for the offline reinforcement learning (RL) problem that we will refer to as return-conditioned supervised learning (RCSL).

D4RL reinforcement-learning +1

On Feature Learning in Neural Networks with Global Convergence Guarantees

no code implementations22 Apr 2022 Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna

We study the optimization of wide neural networks (NNs) via gradient flow (GF) in setups that allow feature learning while admitting non-asymptotic global convergence guarantees.

Extended Unconstrained Features Model for Exploring Deep Neural Collapse

no code implementations16 Feb 2022 Tom Tirer, Joan Bruna

Specifically, it has been shown that the learned features (the output of the penultimate layer) of within-class samples converge to their mean, and the means of different classes exhibit a certain tight frame structure, which is also aligned with the last layer's weights.

Simultaneous Transport Evolution for Minimax Equilibria on Measures

no code implementations14 Feb 2022 Carles Domingo-Enrich, Joan Bruna

Min-max optimization problems arise in several key machine learning setups, including adversarial learning and generative modeling.

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

no code implementations7 Dec 2021 Ilias Zadik, Min Jae Song, Alexander S. Wein, Joan Bruna

Prior work on many similar inference tasks portends that such lower bounds strongly suggest the presence of an inherent statistical-to-computational gap for clustering, that is, a parameter regime where the clustering task is statistically possible but no polynomial-time algorithm succeeds.


Quantile Filtered Imitation Learning

no code implementations2 Dec 2021 David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna

We introduce quantile filtered imitation learning (QFIL), a novel policy improvement operator designed for offline reinforcement learning.

D4RL Imitation Learning

On the Sample Complexity of Learning under Geometric Stability

no code implementations NeurIPS 2021 Alberto Bietti, Luca Venturi, Joan Bruna

Many supervised learning problems involve high-dimensional data such as images, text, or graphs.

Multi-fidelity Stability for Graph Representation Learning

no code implementations25 Nov 2021 Yihan He, Joan Bruna

In this example, we provide non-asymptotic bounds that highly depend on the sparsity of the receptive field constructed by the algorithm.

Graph Representation Learning Structured Prediction

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

no code implementations12 Oct 2021 Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok

We present the Rate-Distortion Explanation (RDE) framework, a mathematically well-founded method for explaining black-box model decisions.

Physical Simulations

Cartoon Explanations of Image Classifiers

1 code implementation7 Oct 2021 Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok

We present CartoonX (Cartoon Explanation), a novel model-agnostic explanation method tailored towards image classifiers and based on the rate-distortion explanation (RDE) framework.

On feature learning in shallow and multi-layer neural networks with global convergence guarantees

no code implementations ICLR 2022 Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna

We study the optimization of over-parameterized shallow and multi-layer neural networks (NNs) in a regime that allows feature learning while admitting non-asymptotic global convergence guarantees.

An Extensible Benchmark Suite for Learning to Simulate Physical Systems

1 code implementation9 Aug 2021 Karl Otness, Arvi Gjoka, Joan Bruna, Daniele Panozzo, Benjamin Peherstorfer, Teseo Schneider, Denis Zorin

Simulating physical systems is a core component of scientific computing, encompassing a wide range of physical domains and applications.

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

no code implementations11 Jul 2021 Carles Domingo-Enrich, Alberto Bietti, Marylou Gabrié, Joan Bruna, Eric Vanden-Eijnden

In the feature-learning regime, this dual formulation justifies using a two time-scale gradient ascent-descent (GDA) training algorithm in which one updates concurrently the particles in the sample space and the neurons in the parameter space of the energy.

On the Cryptographic Hardness of Learning Single Periodic Neurons

no code implementations NeurIPS 2021 Min Jae Song, Ilias Zadik, Joan Bruna

More precisely, our reduction shows that any polynomial-time algorithm (not necessarily gradient-based) for learning such functions under small noise implies a polynomial-time quantum algorithm for solving worst-case lattice problems, whose hardness form the foundation of lattice-based cryptography.


Offline RL Without Off-Policy Evaluation

1 code implementation NeurIPS 2021 David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna

In addition, we hypothesize that the strong performance of the one-step algorithm is due to a combination of favorable structure in the environment and behavior policy.

D4RL Offline RL +1

On the Sample Complexity of Learning under Invariance and Geometric Stability

no code implementations14 Jun 2021 Alberto Bietti, Luca Venturi, Joan Bruna

Many supervised learning problems involve high-dimensional data such as images, text, or graphs.

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

5 code implementations27 Apr 2021 Michael M. Bronstein, Joan Bruna, Taco Cohen, Petar Veličković

The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods.

Protein Folding

On Energy-Based Models with Overparametrized Shallow Neural Networks

1 code implementation15 Apr 2021 Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna

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

Symmetry Breaking in Symmetric Tensor Decomposition

no code implementations10 Mar 2021 Yossi Arjevani, Joan Bruna, Michael Field, Joe Kileel, Matthew Trager, Francis Williams

In this note, we consider the optimization problem associated with computing the rank decomposition of a symmetric tensor.

Tensor Decomposition

Depth separation beyond radial functions

no code implementations2 Feb 2021 Luca Venturi, Samy Jelassi, Tristan Ozuch, Joan Bruna

The first contribution of this paper is to extend such results to a more general class of functions, namely functions with piece-wise oscillatory structure, by building on the proof strategy of (Eldan and Shamir, 2016).

Self-Supervised Equivariant Scene Synthesis from Video

no code implementations1 Feb 2021 Cinjon Resnick, Or Litany, Cosmas Heiß, Hugo Larochelle, Joan Bruna, Kyunghyun Cho

We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations.

Learned Equivariant Rendering without Transformation Supervision

no code implementations11 Nov 2020 Cinjon Resnick, Or Litany, Hugo Larochelle, Joan Bruna, Kyunghyun Cho

We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background.

On Graph Neural Networks versus Graph-Augmented MLPs

1 code implementation ICLR 2021 Lei Chen, Zhengdao Chen, Joan Bruna

From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments node features with certain multi-hop operators on the graph and then applies an MLP in a node-wise fashion.

Community Detection Isomorphism Testing

Kernel-Based Smoothness Analysis of Residual Networks

1 code implementation21 Sep 2020 Tom Tirer, Joan Bruna, Raja Giryes

A major factor in the success of deep neural networks is the use of sophisticated architectures rather than the classical multilayer perceptron (MLP).

A Dynamical Central Limit Theorem for Shallow Neural Networks

no code implementations NeurIPS 2020 Zhengdao Chen, Grant M. Rotskoff, Joan Bruna, Eric Vanden-Eijnden

Furthermore, if the mean-field dynamics converges to a measure that interpolates the training data, we prove that the asymptotic deviation eventually vanishes in the CLT scaling.

A Functional Perspective on Learning Symmetric Functions with Neural Networks

no code implementations16 Aug 2020 Aaron Zweig, Joan Bruna

Symmetric functions, which take as input an unordered, fixed-size set, are known to be universally representable by neural networks that enforce permutation invariance.

Generalization Bounds

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

no code implementations28 Jul 2020 Donsub Rim, Luca Venturi, Joan Bruna, Benjamin Peherstorfer

Classical reduced models are low-rank approximations using a fixed basis designed to achieve dimensionality reduction of large-scale systems.

Dimensionality Reduction

In-Distribution Interpretability for Challenging Modalities

no code implementations1 Jul 2020 Cosmas Heiß, Ron Levie, Cinjon Resnick, Gitta Kutyniok, Joan Bruna

It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches.

Physical Simulations

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

1 code implementation CVPR 2021 Francis Williams, Matthew Trager, Joan Bruna, Denis Zorin

We present Neural Splines, a technique for 3D surface reconstruction that is based on random feature kernels arising from infinitely-wide shallow ReLU networks.

Surface Reconstruction

On Sparsity in Overparametrised Shallow ReLU Networks

no code implementations18 Jun 2020 Jaume de Dios, Joan Bruna

The analysis of neural network training beyond their linearization regime remains an outstanding open question, even in the simplest setup of a single hidden-layer.

Open-Ended Question Answering

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

no code implementations NeurIPS 2020 Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin

We introduce a framework for designing primal methods under the decentralized optimization setting where local functions are smooth and strongly convex.

Continuous LWE

no code implementations19 May 2020 Joan Bruna, Oded Regev, Min Jae Song, Yi Tang

We introduce a continuous analogue of the Learning with Errors (LWE) problem, which we name CLWE.

Open-Ended Question Answering

A Permutation-Equivariant Neural Network Architecture For Auction Design

1 code implementation2 Mar 2020 Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg

Designing an incentive compatible auction that maximizes expected revenue is a central problem in Auction Design.

Provably Efficient Third-Person Imitation from Offline Observation

no code implementations27 Feb 2020 Aaron Zweig, Joan Bruna

Domain adaptation in imitation learning represents an essential step towards improving generalizability.

Domain Adaptation Imitation Learning

Can Graph Neural Networks Count Substructures?

1 code implementation NeurIPS 2020 Zhengdao Chen, Lei Chen, Soledad Villar, Joan Bruna

We also prove positive results for k-WL and k-IGNs as well as negative results for k-WL with a finite number of iterations.

Isomorphism Testing

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

no code implementations30 Nov 2019 Cinjon Resnick, Zeping Zhan, Joan Bruna

Our first contribution is to show that this test is insufficient and that models which perform poorly (strongly) on linear classification can perform strongly (weakly) on more involved tasks like temporal activity localization.


Stability of Graph Neural Networks to Relative Perturbations

no code implementations21 Oct 2019 Fernando Gama, Joan Bruna, Alejandro Ribeiro

In this paper, we are set to study the effect that a change in the underlying graph topology that supports the signal has on the output of a GNN.

Movie Recommendation Recommendation Systems

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

no code implementations ICLR 2020 Matthew Trager, Kathlén Kohn, Joan Bruna

The critical locus of the loss function of a neural network is determined by the geometry of the functional space and by the parameterization of this space by the network's weights.

Projected Canonical Decomposition for Knowledge Base Completion

no code implementations25 Sep 2019 Timothée Lacroix, Guillaume Obozinski, Joan Bruna, Nicolas Usunier

However, as we show in this paper through experiments on standard benchmarks of link prediction in knowledge bases, ComplEx, a variant of CP, achieves similar performances to recent approaches based on Tucker decomposition on all operating points in terms of number of parameters.

Knowledge Base Completion Link Prediction

Gradient Dynamics of Shallow Univariate ReLU Networks

no code implementations NeurIPS 2019 Francis Williams, Matthew Trager, Claudio Silva, Daniele Panozzo, Denis Zorin, Joan Bruna

We show that the gradient dynamics of such networks are determined by the gradient flow in a non-redundant parameterization of the network function.

Stability of Graph Scattering Transforms

1 code implementation NeurIPS 2019 Fernando Gama, Joan Bruna, Alejandro Ribeiro

In this work, we extend scattering transforms to network data by using multiresolution graph wavelets, whose computation can be obtained by means of graph convolutions.

Transfer Learning

On the Expressive Power of Deep Polynomial Neural Networks

1 code implementation NeurIPS 2019 Joe Kileel, Matthew Trager, Joan Bruna

We study deep neural networks with polynomial activations, particularly their expressive power.

Geometric Insights into the Convergence of Nonlinear TD Learning

no code implementations ICLR 2020 David Brandfonbrener, Joan Bruna

Then, we show how environments that are more reversible induce dynamics that are better for TD learning and prove global convergence to the true value function for well-conditioned function approximators.

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

1 code implementation NeurIPS 2019 Zhengdao Chen, Soledad Villar, Lei Chen, Joan Bruna

We further develop a framework of the expressive power of GNNs that incorporates both of these viewpoints using the language of sigma-algebra, through which we compare the expressive power of different types of GNNs together with other graph isomorphism tests.

Graph Regression Isomorphism Testing

Extragradient with player sampling for faster Nash equilibrium finding

1 code implementation29 May 2019 Carles Domingo Enrich, Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna

Data-driven modeling increasingly requires to find a Nash equilibrium in multi-player games, e. g. when training GANs.

Stability Properties of Graph Neural Networks

no code implementations11 May 2019 Fernando Gama, Joan Bruna, Alejandro Ribeiro

Graph neural networks (GNNs) have emerged as a powerful tool for nonlinear processing of graph signals, exhibiting success in recommender systems, power outage prediction, and motion planning, among others.

Motion Planning Recommendation Systems

Backplay: 'Man muss immer umkehren'

no code implementations ICLR 2019 Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor, Alexander Peysakhovich, Kyunghyun Cho, Joan Bruna

Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.

Reinforcement Learning (RL)

Advancing GraphSAGE with A Data-Driven Node Sampling

1 code implementation29 Apr 2019 Jihun Oh, Kyunghyun Cho, Joan Bruna

As an efficient and scalable graph neural network, GraphSAGE has enabled an inductive capability for inferring unseen nodes or graphs by aggregating subsampled local neighborhoods and by learning in a mini-batch gradient descent fashion.

General Classification Node Classification

Global convergence of neuron birth-death dynamics

no code implementations5 Feb 2019 Grant Rotskoff, Samy Jelassi, Joan Bruna, Eric Vanden-Eijnden

Neural networks with a large number of parameters admit a mean-field description, which has recently served as a theoretical explanation for the favorable training properties of "overparameterized" models.

Community Detection with Graph Neural Networks

2 code implementations ICLR 2018 Zhengdao Chen, Xiang Li, Joan Bruna

This graph inference task can be recast as a node-wise graph classification problem, and, as such, computational detection thresholds can be translated in terms of learning within appropriate models.

Community Detection Graph Classification +1

Graph Neural Networks for IceCube Signal Classification

1 code implementation17 Sep 2018 Nicholas Choma, Federico Monti, Lisa Gerhardt, Tomasz Palczewski, Zahra Ronaghi, Prabhat, Wahid Bhimji, Michael M. Bronstein, Spencer R. Klein, Joan Bruna

Tasks involving the analysis of geometric (graph- and manifold-structured) data have recently gained prominence in the machine learning community, giving birth to a rapidly developing field of geometric deep learning.

Classification General Classification

Planning with Arithmetic and Geometric Attributes

no code implementations6 Sep 2018 David Folqué, Sainbayar Sukhbaatar, Arthur Szlam, Joan Bruna

A desirable property of an intelligent agent is its ability to understand its environment to quickly generalize to novel tasks and compose simpler tasks into more complex ones.

Backplay: "Man muss immer umkehren"

1 code implementation18 Jul 2018 Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor, Alexander Peysakhovich, Kyunghyun Cho, Joan Bruna

Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.

Reinforcement Learning (RL)

Spurious Valleys in Two-layer Neural Network Optimization Landscapes

no code implementations18 Feb 2018 Luca Venturi, Afonso S. Bandeira, Joan Bruna

Focusing on a class of two-layer neural networks defined by smooth (but generally non-linear) activation functions, we identify a notion of intrinsic dimension and show that it provides necessary and sufficient conditions for the absence of spurious valleys.

Vocal Bursts Valence Prediction

Multiscale Sparse Microcanonical Models

no code implementations6 Jan 2018 Joan Bruna, Stephane Mallat

Asymptotic properties of maximum entropy microcanonical and macrocanonical processes and their convergence to Gibbs measures are reviewed.

Gaussian Processes Point Processes +1

Mathematics of Deep Learning

no code implementations13 Dec 2017 Rene Vidal, Joan Bruna, Raja Giryes, Stefano Soatto

Recently there has been a dramatic increase in the performance of recognition systems due to the introduction of deep architectures for representation learning and classification.

General Classification Representation Learning

Few-Shot Learning with Graph Neural Networks

6 code implementations10 Nov 2017 Victor Garcia, Joan Bruna

We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not.

Active Learning Few-Shot Learning

Revised Note on Learning Algorithms for Quadratic Assignment with Graph Neural Networks

3 code implementations22 Jun 2017 Alex Nowak, Soledad Villar, Afonso S. Bandeira, Joan Bruna

Inverse problems correspond to a certain type of optimization problems formulated over appropriate input distributions.

Understanding the Learned Iterative Soft Thresholding Algorithm with matrix factorization

1 code implementation2 Jun 2017 Thomas Moreau, Joan Bruna

Sparse coding is a core building block in many data analysis and machine learning pipelines.

Surface Networks

1 code implementation CVPR 2018 Ilya Kostrikov, Zhongshi Jiang, Daniele Panozzo, Denis Zorin, Joan Bruna

We study data-driven representations for three-dimensional triangle meshes, which are one of the prevalent objects used to represent 3D geometry.

Supervised Community Detection with Line Graph Neural Networks

4 code implementations ICLR 2019 Zhengdao Chen, Xiang Li, Joan Bruna

We show that, in a data-driven manner and without access to the underlying generative models, they can match or even surpass the performance of the belief propagation algorithm on binary and multi-class stochastic block models, which is believed to reach the computational threshold.

 Ranked #1 on Community Detection on Amazon (Accuracy-NE metric, using extra training data)

Community Detection Graph Classification +1

Geometric deep learning: going beyond Euclidean data

no code implementations24 Nov 2016 Michael M. Bronstein, Joan Bruna, Yann Lecun, Arthur Szlam, Pierre Vandergheynst

In many applications, such geometric data are large and complex (in the case of social networks, on the scale of billions), and are natural targets for machine learning techniques.

Divide and Conquer Networks

1 code implementation ICLR 2018 Alex Nowak-Vila, David Folqué, Joan Bruna

Moreover, thanks to the dynamic aspect of our architecture, we can incorporate the computational complexity as a regularization term that can be optimized by backpropagation.

Clustering Inductive Bias

Topology and Geometry of Half-Rectified Network Optimization

1 code implementation4 Nov 2016 C. Daniel Freeman, Joan Bruna

Our theoretical work quantifies and formalizes two important \emph{folklore} facts: (i) the landscape of deep linear networks has a radically different topology from that of deep half-rectified ones, and (ii) that the energy landscape in the non-linear case is fundamentally controlled by the interplay between the smoothness of the data distribution and model over-parametrization.

Voice Conversion using Convolutional Neural Networks

1 code implementation27 Oct 2016 Shariq Mobin, Joan Bruna

The human auditory system is able to distinguish the vocal source of thousands of speakers, yet not much is known about what features the auditory system uses to do this.

Voice Conversion

Inverse Problems with Invariant Multiscale Statistics

no code implementations18 Sep 2016 Ivan Dokmanić, Joan Bruna, Stéphane Mallat, Maarten de Hoop

We propose a new approach to linear ill-posed inverse problems.

Computational Engineering, Finance, and Science

Understanding Trainable Sparse Coding via Matrix Factorization

1 code implementation1 Sep 2016 Thomas Moreau, Joan Bruna

Sparse coding is a core building block in many data analysis and machine learning pipelines.

Super-Resolution with Deep Convolutional Sufficient Statistics

1 code implementation18 Nov 2015 Joan Bruna, Pablo Sprechmann, Yann Lecun

Inverse problems in image and audio, and super-resolution in particular, can be seen as high-dimensional structured prediction problems, where the goal is to characterize the conditional distribution of a high-resolution output given its low-resolution corrupted observation.

Bandwidth Extension Image Super-Resolution +1

Deep Convolutional Networks on Graph-Structured Data

3 code implementations16 Jun 2015 Mikael Henaff, Joan Bruna, Yann Lecun

Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions.

General Classification

A mathematical motivation for complex-valued convolutional networks

no code implementations11 Mar 2015 Joan Bruna, Soumith Chintala, Yann Lecun, Serkan Piantino, Arthur Szlam, Mark Tygert

Courtesy of the exact correspondence, the remarkably rich and rigorous body of mathematical analysis for wavelets applies directly to (complex-valued) convnets.

Audio Source Separation with Discriminative Scattering Networks

no code implementations22 Dec 2014 Pablo Sprechmann, Joan Bruna, Yann Lecun

In this report we describe an ongoing line of research for solving single-channel source separation problems.

Audio Source Separation

Training Convolutional Networks with Noisy Labels

no code implementations9 Jun 2014 Sainbayar Sukhbaatar, Joan Bruna, Manohar Paluri, Lubomir Bourdev, Rob Fergus

The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results.

General Classification

Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation

no code implementations NeurIPS 2014 Emily Denton, Wojciech Zaremba, Joan Bruna, Yann Lecun, Rob Fergus

We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks.

Object Recognition

Spectral Networks and Locally Connected Networks on Graphs

4 code implementations21 Dec 2013 Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann Lecun

Convolutional Neural Networks are extremely efficient architectures in image and audio recognition tasks, thanks to their ability to exploit the local translational invariance of signal classes over their domain.

Clustering Translation

Intriguing properties of neural networks

11 code implementations21 Dec 2013 Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks.

Blind Deconvolution with Non-local Sparsity Reweighting

no code implementations16 Nov 2013 Dilip Krishnan, Joan Bruna, Rob Fergus

Blind deconvolution has made significant progress in the past decade.

Signal Recovery from Pooling Representations

no code implementations16 Nov 2013 Joan Bruna, Arthur Szlam, Yann Lecun

In this work we compute lower Lipschitz bounds of $\ell_p$ pooling operators for $p=1, 2, \infty$ as well as $\ell_p$ pooling operators preceded by half-rectification layers.


Invariant Scattering Convolution Networks

1 code implementation5 Mar 2012 Joan Bruna, Stéphane Mallat

A wavelet scattering network computes a translation invariant image representation, which is stable to deformations and preserves high frequency information for classification.

Classification General Classification +1

Classification with Scattering Operators

no code implementations12 Nov 2010 Joan Bruna, Stéphane Mallat

A scattering vector is a local descriptor including multiscale and multi-direction co-occurrence information.

Classification General Classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.