Distributed Coordinate Descent for Generalized Linear Models with Regularization

TL;DR

This paper introduces a scalable distributed coordinate descent algorithm for regularized generalized linear models, effectively handling large, sparse datasets in cluster environments with proven convergence.

Contribution

It presents a novel feature-wise data splitting and coordinate descent algorithm with convergence proof, optimized for distributed environments and large-scale sparse data.

Findings

Algorithm is scalable and efficient on large datasets

Outperforms existing methods in speed and accuracy for sparse data

Addresses slow node issues with modifications

Abstract

Generalized linear model with $L_1$ and $L_2$ regularization is a widely used technique for solving classification, class probability estimation and regression problems. With the numbers of both features and examples growing rapidly in the fields like text mining and clickstream data analysis parallelization and the use of cluster architectures becomes important. We present a novel algorithm for fitting regularized generalized linear models in the distributed environment. The algorithm splits data between nodes by features, uses coordinate descent on each node and line search to merge results globally. Convergence proof is provided. A modifications of the algorithm addresses slow node problem. For an important particular case of logistic regression we empirically compare our program with several state-of-the art approaches that rely on different algorithmic and data spitting methods. Experiments demonstrate that our approach is scalable and superior when training on large and sparse datasets.