353 citations · 1.8k across the 69 of their papers we have counts for
80 papers
Temporal network compression via network hashing
Rémi Vaudaine, Pierre Borgnat, Paulo Goncalves +2
Pairwise temporal interactions between entities can be represented as temporal networks, which code the propagation of processes such as epidemic spreading or information cascades,…
Butterfly factorization by algorithmic identification of rank-one blocks
Léon Zheng, Gilles Puy, Elisa Riccietti +2
Many matrices associated with fast transforms posess a certain low-rank property characterized by the existence of several block partitionings of the matrix, where each block is of…
Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows
Sibylle Marcotte, Rémi Gribonval, Gabriel Peyré
Understanding the geometric properties of gradient descent dynamics is a key ingredient in deciphering the recent success of very large machine learning models. A striking observat…
Does a sparse ReLU network training problem always admit an optimum?
Quoc-Tung Le, Elisa Riccietti, Rémi Gribonval
Given a training set, a loss function, and a neural network architecture, it is often taken for granted that optimal network parameters exist, and a common practice is to apply ava…
Private Statistical Estimation of Many Quantiles
Clément Lalanne, Aurélien Garivier, Rémi Gribonval
This work studies the estimation of many statistical quantiles under differential privacy. More precisely, given a distribution and access to i.i.d. samples from it, we study the e…
On the Statistical Complexity of Estimation and Testing under Privacy Constraints
Clément Lalanne, Aurélien Garivier, Rémi Gribonval
The challenge of producing accurate statistics while respecting the privacy of the individuals in a sample is an important area of research. We study minimax lower bounds for class…
Self-supervised learning with rotation-invariant kernels
Léon Zheng, Gilles Puy, Elisa Riccietti +2
We introduce a regularization loss based on kernel mean embeddings with rotation-invariant kernels on the hypersphere (also known as dot-product kernels) for self-supervised learni…
Compressive Clustering with an Optical Processing Unit
Luc Giffon, Rémi Gribonval
We explore the use of Optical Processing Units (OPU) to compute random Fourier features for sketching, and adapt the overall compressive clustering pipeline to this setting. We als…
Private Quantiles Estimation in the Presence of Atoms
Clément Sébastien Lalanne, Clément Gastaud, Nicolas Grislain +2
We consider the differentially private estimation of multiple quantiles (MQ) of a distribution from a dataset, a key building block in modern data analysis. We apply the recent non…
A theory of optimal convex regularization for low-dimensional recovery
Yann Traonmilin, Rémi Gribonval, Samuel Vaiter
We consider the problem of recovering elements of a low-dimensional model from under-determined linear measurements. To perform recovery, we consider the minimization of a convex r…
Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning
Titouan Vayer, Rémi Gribonval
Comparing probability distributions is at the crux of many machine learning algorithms. Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of distances betw…
Spurious Valleys, NP-hardness, and Tractability of Sparse Matrix Factorization With Fixed Support
Quoc-Tung Le, Elisa Riccietti, Rémi Gribonval
The problem of approximating a dense matrix by a product of sparse factors is a fundamental problem for many signal processing and machine learning tasks. It can be decomposed into…
Identifiability in Two-Layer Sparse Matrix Factorization
Léon Zheng, Elisa Riccietti, Rémi Gribonval
Sparse matrix factorization is the problem of approximating a matrix by a product of sparse factors .…
Efficient Identification of Butterfly Sparse Matrix Factorizations
Léon Zheng, Elisa Riccietti, Rémi Gribonval
Fast transforms correspond to factorizations of the form , where each factor is sparse and possibly st…
Nonsmooth convex optimization to estimate the Covid-19 reproduction number space-time evolution with robustness against low quality data
Barbara Pascal, Patrice Abry, Nelly Pustelnik +3
Daily pandemic surveillance, often achieved through the estimation of the reproduction number, constitutes a critical challenge for national health authorities to design countermea…
An Embedding of ReLU Networks and an Analysis of their Identifiability
Pierre Stock, Rémi Gribonval
Neural networks with the Rectified Linear Unit (ReLU) nonlinearity are described by a vector of parameters , and realized as a piecewise linear continuous function $R_θ: x \in \…
Fast Multiscale Diffusion on Graphs
Sibylle Marcotte, Amélie Barbe, Rémi Gribonval +4
Diffusing a graph signal at multiple scales requires computing the action of the exponential of several multiples of the Laplacian matrix. We tighten a bound on the approximation e…
Minibatch optimal transport distances; analysis and applications
Kilian Fatras, Younes Zine, Szymon Majewski +3
Optimal transport distances have become a classic tool to compare probability distributions and have found many applications in machine learning. Yet, despite recent algorithmic de…
Continuous dictionaries meet low-rank tensor approximations
Clement Elvira, Jeremy E. Cohen, Cedric Herzet +1
In this short paper we bridge two seemingly unrelated sparse approximation topics: continuous sparse coding and low-rank approximations. We show that for a specific choice of conti…
Sketching Datasets for Large-Scale Learning (long version)
Rémi Gribonval, Antoine Chatalic, Nicolas Keriven +3
This article considers "compressive learning," an approach to large-scale machine learning where datasets are massively compressed before learning (e.g., clustering, classification…
Sparsity-based audio declipping methods: selected overview, new algorithms, and large-scale evaluation
Clément Gaultier, Srđan Kitić, Rémi Gribonval +1
Recent advances in audio declipping have substantially improved the state of the art.% in certain saturation regimes. Yet, practitioners need guidelines to choose a method, and whi…
Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling
Rémi Gribonval, Gilles Blanchard, Nicolas Keriven +1
We provide statistical learning guarantees for two unsupervised learning tasks in the context of compressive statistical learning, a general framework for resource-efficient large-…
Training with Quantization Noise for Extreme Model Compression
Angela Fan, Pierre Stock, Benjamin Graham +4
We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, wher…
Fast Optical System Identification by Numerical Interferometry
Sidharth Gupta, Rémi Gribonval, Laurent Daudet +1
We propose a numerical interferometry method for identification of optical multiply-scattering systems when only intensity can be measured. Our method simplifies the calibration of…