Session IV
| Speaker | Title tap/hover for abstract | Materials |
|---|---|---|
| Michael UnserBiomedical Imaging Group EPFL, CH | Representer theorems for machine learning and inverse problems Representer theorems for machine learning and inverse problems Regularization addresses the ill-posedness of the training problem in machine learning or the reconstruction of a signal from a limited number of measurements. The standard strategy consists in augmenting the original cost functional by an energy that penalizes solutions with undesirable behaviour. In this presentation, I will present a general representer theorem that characterizes the solutions of a remarkably broad class of optimization problems in Banach spaces and helps us understand the effect of regularization. I will then use the theorem to retrieve some classical characterizations such as the celebrated representer theorem of machine leaning for RKHS, Tikhonov regularization, representer theorems for sparsity promoting functionals, as well as a few new ones, including a result for deep neural networks. |
video slides |
| Vincent DuvalInria, FR | Representing the solutions of total variation regularized problems Representing the solutions of total variation regularized problems The total (gradient) variation is a regularizer which has been widely used in inverse problems arising in image processing, following the pioneering work of Rudin, Osher and Fatemi. In this talk, I will describe the structure the solutions to the total variation regularized variational problems when one has a finite number of measurements. First, I will present a general representation principle for the solutions of convex problems, then I will apply it to the total variation by describing the faces of its unit ball. It is a joint work with Claire Boyer, Antonin Chambolle, Yohann De Castro, Frédéric de Gournay and Pierre Weiss. |
video slides |
Video Recordings
Michael Unser: Representer theorems for machine learning and inverse problems
Abstract: Regularization addresses the ill-posedness of the training problem in machine learning or the reconstruction of a signal from a limited number of measurements. The standard strategy consists in augmenting the original cost functional by an energy that penalizes solutions with undesirable behaviour. In this presentation, I will present a general representer theorem that characterizes the solutions of a remarkably broad class of optimization problems in Banach spaces and helps us understand the effect of regularization. I will then use the theorem to retrieve some classical characterizations such as the celebrated representer theorem of machine leaning for RKHS, Tikhonov regularization, representer theorems for sparsity promoting functionals, as well as a few new ones, including a result for deep neural networks.
Vincent Duval: Representing the solutions of total variation regularized problems
Abstract: The total (gradient) variation is a regularizer which has been widely used in inverse problems arising in image processing, following the pioneering work of Rudin, Osher and Fatemi. In this talk, I will describe the structure the solutions to the total variation regularized variational problems when one has a finite number of measurements.
First, I will present a general representation principle for the solutions of convex problems, then I will apply it to the total variation by describing the faces of its unit ball.
It is a joint work with Claire Boyer, Antonin Chambolle, Yohann De Castro, Frédéric de Gournay and Pierre Weiss.