Search results for "Proximal Gradient Methods"
showing 3 items of 3 documents
Online Hyperparameter Search Interleaved with Proximal Parameter Updates
2021
There is a clear need for efficient hyperparameter optimization (HO) algorithms for statistical learning, since commonly applied search methods (such as grid search with N-fold cross-validation) are inefficient and/or approximate. Previously existing gradient-based HO algorithms that rely on the smoothness of the cost function cannot be applied in problems such as Lasso regression. In this contribution, we develop a HO method that relies on the structure of proximal gradient methods and does not require a smooth cost function. Such a method is applied to Leave-one-out (LOO)-validated Lasso and Group Lasso, and an online variant is proposed. Numerical experiments corroborate the convergence …
Least-Norm Regularization For Weak Two-Level Optimization Problems
1992
In this paper, we consider a regularization for weak two-level optimization problems by adaptation of the method presented by Solohovic (1970). Existence and approximation results are given in the case in which the constraints to the lower level problems are described by a multifunction. Convergence results for the least-norm regularization under perturbations are also presented.
About the finite convergence of the proximal point algorithm
1988
We study the finite convergence property of the proximal point algorithm applied to the partial inverse, with respect to a subspace, of the subdifferential of a polyhedral convex function. Using examples we show how sufficient conditions providing the finite convergence can be realized and we give a case with non finite termination.