A Blockwise Descent Algorithm for Group-penalized Multiresponse and Multinomial Regression

TL;DR

This paper introduces a blockwise descent algorithm for efficient group-penalized multiresponse and multinomial regression, demonstrating significant speed improvements and real-time capabilities for large-scale gene-expression data analysis.

Contribution

The paper presents a novel blockwise descent algorithm extended to multinomial regression within a quasi-Newton framework, with an open-source R implementation.

Findings

Algorithm is an order of magnitude faster than competitors.

Can solve gene-expression-sized problems in real time.

Provides publicly available implementation for broader use.

Abstract

In this paper we purpose a blockwise descent algorithm for group-penalized multiresponse regression. Using a quasi-newton framework we extend this to group-penalized multinomial regression. We give a publicly available implementation for these in R, and compare the speed of this algorithm to a competing algorithm --- we show that our implementation is an order of magnitude faster than its competitor, and can solve gene-expression-sized problems in real time.