Coordinate Descent for SLOPE

Summary, in English

The lasso is the most famous sparse regression and feature selection method. One reason for its popularity is the speed at which the underlying optimization problem can be solved. Sorted L-One Penalized Estimation (SLOPE) is a generalization of the lasso with appealing statistical properties. In spite of this, the method has not yet reached widespread interest. A major reason for this is that current software packages that fit SLOPE rely on algorithms that perform poorly in high dimensions. To tackle this issue, we propose a new fast algorithm to solve the SLOPE optimization problem, which combines proximal gradient descent and proximal coordinate descent steps. We provide new results on the directional derivative of the SLOPE penalty and its related SLOPE thresholding operator, as well as provide convergence guarantees for our proposed solver. In extensive benchmarks on simulated and real data, we demonstrate our method's performance against a long list of competing algorithms.

• Author: Johan Larsson; Quentin Klopfenstein; Mathurin Massias; Jonas Wallin
• Editor: Francisco Ruiz; Jennifer Dy; Jan-Willem van de Meent
• Department/s: Department of Statistics
• Publishing year: 2023
• Language: English
• Pages: 4802-4821
• Publication/Series: Proceedings of Machine Learning Research
• Volume: 206
• Links: https://proceedings.mlr.press/v206/larsson23a/larsson23a.pdf
• Document type: Conference paper
• Topic: Probability Theory and Statistics
• Conference name: 26th International Conference on Artificial Intelligence and Statistics, AISTATS 2023
• Conference date: 2023-04-25 - 2023-04-27
• Conference place: Valencia, Spain
• Status: Published