2k citations · 6.6k across the 78 of their papers we have counts for
7 papers · 1 filter
Subsampled online matrix factorization with convergence guarantees
Arthur Mensch, Julien Mairal, Gaël Varoquaux +1
We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i.e., that contains morethan 1TB of data). The algorithm streams the ma…
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure
Alberto Bietti, Julien Mairal
Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal…
An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration
Hongzhou Lin, Julien Mairal, Zaid Harchaoui
We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to inc…
Dictionary Learning for Massive Matrix Factorization
Arthur Mensch, Julien Mairal, Bertrand Thirion +1
Sparse matrix factorization is a popular tool to obtain interpretable data decompositions, which are also effective to perform data completion or denoising. Its applicability to la…
End-to-End Kernel Learning with Supervised Convolutional Kernel Networks
Julien Mairal
In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the predi…
Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach
Mattis Paulin, Julien Mairal, Matthijs Douze +3
Convolutional neural networks (CNNs) have recently received a lot of attention due to their ability to model local stationary structures in natural images in a multi-scale fashion,…
DOLPHIn - Dictionary Learning for Phase Retrieval
Andreas M. Tillmann, Yonina C. Eldar, Julien Mairal
We propose a new algorithm to learn a dictionary for reconstructing and sparsely encoding signals from measurements without phase. Specifically, we consider the task of estimating…