Fast Overlapping Group Lasso
arXiv:1009.0306
Abstract
The group Lasso is an extension of the Lasso for feature selection on (predefined) non-overlapping groups of features. The non-overlapping group structure limits its applicability in practice. There have been several recent attempts to study a more general formulation, where groups of features are given, potentially with overlaps between the groups. The resulting optimization is, however, much more challenging to solve due to the group overlaps. In this paper, we consider the efficient optimization of the overlapping group Lasso penalized problem. We reveal several key properties of the proximal operator associated with the overlapping group Lasso, and compute the proximal operator by solving the smooth and convex dual problem, which allows the use of the gradient descent type of algorithms for the optimization. We have performed empirical evaluations using the breast cancer gene expression data set, which consists of 8,141 genes organized into (overlapping) gene sets. Experimental results demonstrate the efficiency and effectiveness of the proposed algorithm.
References in corpus (2)
Cited by in corpus (12)
- Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
- Smoothing proximal gradient method for general structured sparse regression
- Network Flow Algorithms for Structured Sparsity
- Smoothing Proximal Gradient Method for General Structured Sparse Learning
- Efficient First Order Methods for Linear Composite Regularizers
- Solving OSCAR regularization problems by proximal splitting algorithms
- Multi-scale Mining of fMRI data with Hierarchical Structured Sparsity
- Sufficient reductions in regression with mixed predictors
- r-Instance Learning for Missing People Tweets Identification
- Understanding and Monitoring Human Trafficking via Social Sensors: A Sociological Approach
- Learning Undirected Graphical Models with Structure Penalty
- Proximal methods for the latent group lasso penalty