29 citations · 104 across the 16 of their papers we have counts for
16 papers
A Second-Order Majorant Algorithm for Nonnegative Matrix Factorization
Mai-Quyen Pham, Jérémy Cohen, Thierry Chonavel
Nonnegative Matrix Factorization (NMF) is a fundamental tool in unsupervised learning, widely used for tasks such as dimensionality reduction, feature extraction, representation le…
On the Maximum Hessian Eigenvalue and Generalization
Simran Kaur, Jeremy Cohen, Zachary C. Lipton
The mechanisms by which certain training interventions, such as increasing learning rates and applying batch normalization, improve the generalization of deep networks remains a my…
Dictionary-based Low-Rank Approximations and the Mixed Sparse Coding problem
Jeremy E. Cohen
Constrained tensor and matrix factorization models allow to extract interpretable patterns from multiway data. Therefore identifiability properties and efficient algorithms for con…
Exploring single-song autoencoding schemes for audio-based music structure analysis
Axel Marmoret, Jérémy E. Cohen, Frédéric Bimbot
The ability of deep neural networks to learn complex data relations and representations is established nowadays, but it generally relies on large sets of training data. This work e…
An AO-ADMM approach to constraining PARAFAC2 on all modes
Marie Roald, Carla Schenker, Vince D. Calhoun +4
Analyzing multi-way measurements with variations across one mode of the dataset is a challenge in various fields including data mining, neuroscience and chemometrics. For example,…
Uncovering audio patterns in music with Nonnegative Tucker Decomposition for structural segmentation
Axel Marmoret, Jérémy E. Cohen, Nancy Bertin +1
Recent work has proposed the use of tensor decomposition to model repetitions and to separate tracks in loop-based electronic music. The present work investigates further on the ab…
PARAFAC2 AO-ADMM: Constraints in all modes
Marie Roald, Carla Schenker, Jeremy E. Cohen +1
The PARAFAC2 model provides a flexible alternative to the popular CANDECOMP/PARAFAC (CP) model for tensor decompositions. Unlike CP, PARAFAC2 allows factor matrices in one mode (i.…
Matrix-wise -constrained Sparse Nonnegative Least Squares
Nicolas Nadisic, Jeremy E Cohen, Arnaud Vandaele +1
Nonnegative least squares problems with multiple right-hand sides (MNNLS) arise in models that rely on additive linear combinations. In particular, they are at the core of most non…
Robot Design With Neural Networks, MILP Solvers and Active Learning
Sanjai Narain, Emily Mak, Dana Chee +6
Central to the design of many robot systems and their controllers is solving a constrained blackbox optimization problem. This paper presents CNMA, a new method of solving this pro…
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…
A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
Carla Schenker, Jeremy E. Cohen, Evrim Acar
Coupled matrix and tensor factorizations (CMTF) are frequently used to jointly analyze data from multiple sources, also called data fusion. However, different characteristics of da…
Sparse Separable Nonnegative Matrix Factorization
Nicolas Nadisic, Arnaud Vandaele, Jeremy E. Cohen +1
We propose a new variant of nonnegative matrix factorization (NMF), combining separability and sparsity assumptions. Separability requires that the columns of the first NMF factor…
Computing the proximal operator of the induced matrix norm
Jeremy E. Cohen
In this short article, for any matrix the proximity operator of two induced norms and are derived. Although no close form…
Accelerating Block Coordinate Descent for Nonnegative Tensor Factorization
Andersen Man Shun Ang, Jeremy E. Cohen, Nicolas Gillis +1
This paper is concerned with improving the empirical convergence speed of block-coordinate descent algorithms for approximate nonnegative tensor factorization (NTF). We propose an…
Universal Lipschitz Approximation in Bounded Depth Neural Networks
Jeremy E. J. Cohen, Todd Huster, Ra Cohen
Adversarial attacks against machine learning models are a rather hefty obstacle to our increasing reliance on these models. Due to this, provably robust (certified) machine learnin…
Identifiability of Complete Dictionary Learning
Jérémy E. Cohen, Nicolas Gillis
Sparse component analysis (SCA), also known as complete dictionary learning, is the following problem: Given an input matrix and an integer , find a dictionary with …