no code implementations • NeurIPS 2012 • Nicolas L. Roux, Mark Schmidt, Francis R. Bach
We propose a new stochastic gradient method for optimizing the sum of a finite set of smooth functions, where the sum is strongly convex.
no code implementations • NeurIPS 2012 • Hachem Kadri, Alain Rakotomamonjy, Philippe Preux, Francis R. Bach
We study this problem in the case of kernel ridge regression for functional responses with an lr-norm constraint on the combination coefficients.
no code implementations • NeurIPS 2011 • Eric Moulines, Francis R. Bach
We consider the minimization of a convex objective function defined on a Hilbert space, which is only available through unbiased estimates of its gradients.
no code implementations • NeurIPS 2011 • Francis R. Bach
We consider a class of sparsity-inducing regularization terms based on submodular functions.
no code implementations • NeurIPS 2011 • Mark Schmidt, Nicolas L. Roux, Francis R. Bach
We consider the problem of optimizing the sum of a smooth convex function and a non-smooth convex function using proximal-gradient methods, where an error is present in the calculation of the gradient of the smooth term or in the proximity operator with respect to the second term.
no code implementations • NeurIPS 2011 • Edouard Grave, Guillaume R. Obozinski, Francis R. Bach
This norm, called the trace Lasso, uses the trace norm of the selected covariates, which is a convex surrogate of their rank, as the criterion of model complexity.
no code implementations • NeurIPS 2010 • Francis R. Bach
Sparse methods for supervised learning aim at finding good linear predictors from as few variables as possible, i. e., with small cardinality of their supports.
no code implementations • NeurIPS 2010 • Matthew Hoffman, Francis R. Bach, David M. Blei
We develop an online variational Bayes (VB) algorithm for Latent Dirichlet Allocation (LDA).
no code implementations • NeurIPS 2010 • Julien Mairal, Rodolphe Jenatton, Francis R. Bach, Guillaume R. Obozinski
Our algorithm scales up to millions of groups and variables, and opens up a whole new range of applications for structured sparse models.
no code implementations • NeurIPS 2010 • Armand Joulin, Jean Ponce, Francis R. Bach
To avoid this problem, we introduce a local approximation of this cost function, which leads to a quadratic non-convex optimization problem over a product of simplices.
no code implementations • NeurIPS 2009 • Percy S. Liang, Guillaume Bouchard, Francis R. Bach, Michael. I. Jordan
Many types of regularization schemes have been employed in statistical learning, each one motivated by some assumption about the problem domain.
no code implementations • NeurIPS 2009 • Sylvain Arlot, Francis R. Bach
This paper tackles the problem of selecting among several linear estimators in non-parametric regression; this includes model selection for linear regression, the choice of a regularization parameter in kernel ridge regression or spline smoothing, and the choice of a kernel in multiple kernel learning.
no code implementations • NeurIPS 2008 • Zaïd Harchaoui, Eric Moulines, Francis R. Bach
Change-point analysis of an (unlabelled) sample of observations consists in, first, testing whether a change in the distribution occurs within the sample, and second, if a change occurs, estimating the change-point instant after which the distribution of the observations switches from one distribution to another different distribution.
no code implementations • NeurIPS 2008 • Laurent Jacob, Jean-Philippe Vert, Francis R. Bach
In multi-task learning several related tasks are considered simultaneously, with the hope that by an appropriate sharing of information across tasks, each task may benefit from the others.
no code implementations • NeurIPS 2008 • Julien Mairal, Jean Ponce, Guillermo Sapiro, Andrew Zisserman, Francis R. Bach
It is now well established that sparse signal models are well suited to restoration tasks and can effectively be learned from audio, image, and video data.
no code implementations • NeurIPS 2008 • Cédric Archambeau, Francis R. Bach
We present a generative model for performing sparse probabilistic projections, which includes sparse principal component analysis and sparse canonical correlation analysis as special cases.
no code implementations • NeurIPS 2008 • Francis R. Bach
For supervised and unsupervised learning, positive definite kernels allow to use large and potentially infinite dimensional feature spaces with a computational cost that only depends on the number of observations.
no code implementations • NeurIPS 2007 • Moulines Eric, Francis R. Bach, Zaïd Harchaoui
This provides us with a consistent nonparametric test statistic, for which we derive the asymptotic distribution under the null hypothesis.
no code implementations • NeurIPS 2007 • Francis R. Bach, Zaïd Harchaoui
We present a novel linear clustering framework (Diffrac) which relies on a linear discriminative cost function and a convex relaxation of a combinatorial optimization problem.