One to beat them all: "RYU" -- a unifying framework for the construction of safe balls
arXiv:2312.00640 · doi:10.5802/ojmo.45
Abstract
In this paper, we present a new framework, called "RYU" for constructing "safe" regions -- specifically, bounded sets that are guaranteed to contain the dual solution of a target optimization problem. Our framework applies to the standard case where the objective function is composed of two components: a closed, proper, convex function with Lipschitz-smooth gradient and another closed, proper, convex function. We show that the RYU framework not only encompasses but also improves upon the state-of-the-art methods proposed over the past decade for this class of optimization problems.
arXiv comment19 pages, 1 table
References in corpus (8)
- Safe Feature Elimination for the LASSO and Sparse Supervised Learning Problems
- Safe Screening With Variational Inequalities and Its Application to LASSO
- Mind the duality gap: safer rules for the Lasso
- A Safe Screening Rule for Sparse Logistic Regression
- Safe squeezing for antisparse coding
- Stable safe screening and structured dictionaries for faster L1 regularization
- Dynamic Sasvi: Strong Safe Screening for Norm-Regularized Least Squares
- Screening Rules and its Complexity for Active Set Identification