Group SLOPE - adaptive selection of groups of predictors

TL;DR

This paper introduces gSLOPE, an extension of SLOPE for selecting entire groups of correlated predictors in high-dimensional models, with theoretical guarantees on false discovery rate control and adaptivity.

Contribution

We develop a convex optimization framework for group variable selection, define group FDR, and provide algorithms and theoretical analysis ensuring control and adaptivity.

Findings

gSLOPE controls group FDR at a preset level under orthogonal groups.

The method adapts to unknown sparsity levels.

Simulations demonstrate the effectiveness of gSLOPE.

Abstract

Sorted L-One Penalized Estimation is a relatively new convex optimization procedure which allows for adaptive selection of regressors under sparse high dimensional designs. Here we extend the idea of SLOPE to deal with the situation when one aims at selecting whole groups of explanatory variables instead of single regressors. This approach is particularly useful when variables in the same group are strongly correlated and thus true predictors are difficult to distinguish from their correlated "neighbors"'. We formulate the respective convex optimization problem, gSLOPE (group SLOPE), and propose an efficient algorithm for its solution. We also define a notion of the group false discovery rate (gFDR) and provide a choice of the sequence of tuning parameters for gSLOPE so that gFDR is provably controlled at a prespecified level if the groups of variables are orthogonal to each other. Moreover, we prove that the resulting procedure adapts to unknown sparsity and is asymptotically minimax with respect to the estimation of the proportions of variance of the response variable explained by regressors from different groups. We also provide a method for the choice of the regularizing sequence when variables in different groups are not orthogonal but statistically independent and illustrate its good properties with computer simulations.