International audienceThis paper proposes a learning framework and a set of algorithms for nonsmooth regression, i.e., for learning piecewise smooth target functions with discontinuities in the function itself or the derivatives at unknown locations. In the proposed approach, the model belongs to a class of smooth functions. Though constrained to be globally smooth, the trained model can have very large derivatives at particular locations to approximate the nonsmoothness of the target function. This is obtained through the definition of new regularization terms which penalize the derivatives in a location-dependent manner and training algorithms in the form of convex optimization problems. Examples of application to hybrid dynamical system ...
We propose a general learning based framework for solving nonsmooth and nonconvex image reconstructi...
This thesis is devoted to the development of algorithms for solving nonsmooth nonconvex problems. So...
International audienceWe introduce a general framework for designing and training neural network lay...
We introduce and analyze an algorithm for the minimization of convex functions that are the sum of d...
Recent advances in statistical learning and convex optimization have inspired many successful practi...
2013-2014 > Academic research: refereed > Publication in refereed journalVersion of RecordPublishe
We propose a non-parametric regression method that does not rely on the structure of the ground-trut...
We develop a novel 2D functional learning framework that employs a sparsity-promoting regularization...
International audienceWe introduce a generic scheme to solve non-convex optimization problems using ...
International audienceWe propose a unifying algorithm for non-smooth non-convex optimization. The al...
International audienceSeveral problems in signal processing and machine learning can be casted as op...
International audienceMotivated by applications to machine learning and imaging science, we study a ...
International audienceWe propose a new family of adaptive first-order methods for a class of convex ...
Natural image statistics indicate that we should use non-convex norms for most regularization tasks ...
We propose a non-parametric regression methodology that enforces the regressor to be fully consisten...
We propose a general learning based framework for solving nonsmooth and nonconvex image reconstructi...
This thesis is devoted to the development of algorithms for solving nonsmooth nonconvex problems. So...
International audienceWe introduce a general framework for designing and training neural network lay...
We introduce and analyze an algorithm for the minimization of convex functions that are the sum of d...
Recent advances in statistical learning and convex optimization have inspired many successful practi...
2013-2014 > Academic research: refereed > Publication in refereed journalVersion of RecordPublishe
We propose a non-parametric regression method that does not rely on the structure of the ground-trut...
We develop a novel 2D functional learning framework that employs a sparsity-promoting regularization...
International audienceWe introduce a generic scheme to solve non-convex optimization problems using ...
International audienceWe propose a unifying algorithm for non-smooth non-convex optimization. The al...
International audienceSeveral problems in signal processing and machine learning can be casted as op...
International audienceMotivated by applications to machine learning and imaging science, we study a ...
International audienceWe propose a new family of adaptive first-order methods for a class of convex ...
Natural image statistics indicate that we should use non-convex norms for most regularization tasks ...
We propose a non-parametric regression methodology that enforces the regressor to be fully consisten...
We propose a general learning based framework for solving nonsmooth and nonconvex image reconstructi...
This thesis is devoted to the development of algorithms for solving nonsmooth nonconvex problems. So...
International audienceWe introduce a general framework for designing and training neural network lay...