25 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre National de la Recherche ScientifiqueFR2 papers
- Institut polytechnique de GrenobleFR2 papers
- THOTH: Apprentissage de modèles visuels à partir de données massivesFR2 papers
- Centre Inria de SaclayFR1 paper
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR1 paper
- Institut national de recherche en sciences et technologies du numériqueFR1 paper
- Laboratoire Jean KuntzmannFR1 paper
- Université Grenoble AlpesFR1 paper
- University of WashingtonUS1 paper
5 papers
A Generic Acceleration Framework for Stochastic Composite Optimization
Andrei Kulunchakov, Julien Mairal
In this paper, we introduce various mechanisms to obtain accelerated first-order stochastic optimization algorithms when the objective function is convex or strongly convex. Specif…
Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise
Andrei Kulunchakov, Julien Mairal
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Neste…
Extracting representations of cognition across neuroimaging studies improves brain decoding
Arthur Mensch, Julien Mairal, Bertrand Thirion +1
Cognitive brain imaging is accumulating datasets about the neural substrate of many different mental processes. Yet, most studies are based on few subjects and have low statistical…
Modeling Visual Context is Key to Augmenting Object Detection Datasets
Nikita Dvornik, Julien Mairal, Cordelia Schmid
Performing data augmentation for learning deep neural networks is well known to be important for training visual recognition systems. By artificially increasing the number of train…
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…