Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 58 - Advanced Bayesian Topics (Part 1)
Type: Contributed
Date/Time: Sunday, August 8, 2021 : 3:30 PM to 5:20 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #317732
Title: Unified Reciprocal LASSO Estimation via Least Squares Approximation
Author(s): Erina Paul* and Himel Mallick
Companies: Merck & Co., Inc. and Merck Research Laboratories
Keywords: Reciprocal LASSO; Regularization; Variable selection; Least squares approximation
Abstract:

The primary goal of this project is to extend the reciprocal LASSO for applications to binary and survival outcomes. We consider the least squares approximation as a solver for the reciprocal LASSO problem. The LSA is a general theoretical framework that includes generalized linear models, Cox regression, and many others as special cases. In order to apply this method to reciprocal LASSO regularization, two types of auxiliary variables are introduced to transfer the original reciprocal LASSO problem into an asymptotically equivalent least squares problem. While the existing literature on reciprocal LASSO has mostly focused on linear models, our algorithm can be easily implemented for general likelihoods, providing a flexible framework for variable selection using reciprocal penalties. To handle the computational burden of implementing the resulting procedure, we employ a scalable stochastic search method called Simplified Shotgun Stochastic Search with Screening, which is easy to implement, without requiring any sophisticated optimization package other than a linear equation solver. We examine the effectiveness of our procedure through MC simulations and real data analyses.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program