Title
An efficient algorithm for minimizing multi non-smooth component functions
Document Type
Data
DOI
10.6084/m9.figshare.12844517.v1
Publication Date
1-1-2020
Description
Many problems in statistics and machine learning can be formulated as an optimization problem of a finite sum of non-smooth convex functions. We propose an algorithm to minimize this type of objective functions based on the idea of alternating linearization. Our algorithm retains the simplicity of contemporary methods without any restrictive assumptions on the smoothness of the loss function. We apply our proposed method to solve two challenging problems: overlapping group Lasso and convex regression with sharp partitions (CRISP). Numerical experiments show that our method is superior to the state-of-the-art algorithms, many of which are based on the accelerated proximal gradient method.
Publisher
figshare Academic Research System
Recommended Citation
Pham, Minh; Ninh, Anh; Liu, Yufeng; Le, Hoang (2020), "An efficient algorithm for minimizing multi non-smooth component functions", figshare Academic Research System, doi: 10.6084/m9.figshare.12844517.v1
https://doi.org/10.6084/m9.figshare.12844517.v1
Source Link
https://tandf.figshare.com/articles/dataset/An_efficient_algorithm_for_minimizing_multi_non-smooth_component_functions/12844517/1
