F
Francis Bach
Researcher at French Institute for Research in Computer Science and Automation
Publications - 520
Citations - 60093
Francis Bach is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Convex optimization & Convex function. The author has an hindex of 110, co-authored 484 publications receiving 54944 citations. Previous affiliations of Francis Bach include Microsoft & University of Évry Val d'Essonne.
Papers
More filters
Journal ArticleDOI
Online Learning for Matrix Factorization and Sparse Coding
TL;DR: In this paper, a new online optimization algorithm based on stochastic approximations is proposed to solve the large-scale matrix factorization problem, which scales up gracefully to large data sets with millions of training samples.
Proceedings ArticleDOI
Online dictionary learning for sparse coding
TL;DR: A new online optimization algorithm for dictionary learning is proposed, based on stochastic approximations, which scales up gracefully to large datasets with millions of training samples, and leads to faster performance and better dictionaries than classical batch algorithms for both small and large datasets.
Posted Content
Online Learning for Matrix Factorization and Sparse Coding
TL;DR: A new online optimization algorithm is proposed, based on stochastic approximations, which scales up gracefully to large data sets with millions of training samples, and extends naturally to various matrix factorization formulations, making it suitable for a wide range of learning problems.
Proceedings ArticleDOI
Non-local sparse models for image restoration
TL;DR: Experimental results in image denoising and demosaicking tasks with synthetic and real noise show that the proposed method outperforms the state of the art, making it possible to effectively restore raw images from digital cameras at a reasonable speed and memory cost.
Journal ArticleDOI
Kernel independent component analysis
Francis Bach,Michael I. Jordan +1 more
TL;DR: A class of algorithms for independent component analysis which use contrast functions based on canonical correlations in a reproducing kernel Hilbert space is presented, showing that these algorithms outperform many of the presently known algorithms.