High Performance Computing Applied to Logistic Regression: A CPU and GPU Implementation Comparison

TL;DR

This paper introduces a GPU-accelerated parallel implementation of logistic regression that significantly speeds up processing large datasets while maintaining accuracy, suitable for real-time applications.

Contribution

The paper presents a GPU-based parallel logistic regression algorithm that outperforms CPU implementations in speed, with an accessible Python library for practical use.

Findings

GPU implementation reduces execution time significantly

Maintains comparable F1 scores to CPU versions

Effective for real-time large dataset applications

Abstract

We present a versatile GPU-based parallel version of Logistic Regression (LR), aiming to address the increasing demand for faster algorithms in binary classification due to large data sets. Our implementation is a direct translation of the parallel Gradient Descent Logistic Regression algorithm proposed by X. Zou et al. [12]. Our experiments demonstrate that our GPU-based LR outperforms existing CPU-based implementations in terms of execution time while maintaining comparable f1 score. The significant acceleration of processing large datasets makes our method particularly advantageous for real-time prediction applications like image recognition, spam detection, and fraud detection. Our algorithm is implemented in a ready-to-use Python library available at : https://github.com/NechbaMohammed/SwiftLogisticReg