Group COMBSS: Group Selection via Continuous Optimization

• DOI: 10.48550/arxiv.2404.13339
• Publication Date: 2024-04-20
• Authors: Anant Mathur; Sarat Moka; Benoît Liquet; Zdravko I. Botev
• Keywords: Group Selection

We present a new optimization method for the group selection problem in linear regression. In this problem, predictors are assumed to have natural structure and goal is select small set of groups that best fits response. The incorporation predictor matrix key factor obtaining better estimators identifying associations between response predictors. Such discrete constrained well-known be hard, particularly high-dimensional settings where number much larger than observations. propose tackle by framing underlying binary into an unconstrained continuous problem. performance our proposed approach compared state-of-the-art variable strategies on simulated data sets. illustrate effectiveness genetic dataset identify grouping markers across chromosomes.