A GPU Implementation of Multi-Guiding Spark Fireworks Algorithm for Efficient Black-Box Neural Network Optimization

TL;DR

This paper introduces a GPU-accelerated Multi-Guiding Spark Fireworks Algorithm that significantly enhances the efficiency of black-box neural network optimization, enabling faster convergence and better performance for large-scale problems.

Contribution

The paper presents a novel GPU implementation of MGFWA, improving its computational speed and solution quality for large-scale neural network optimization tasks.

Findings

GPU-MGFWA outperforms CPU-based version in speed and accuracy.

Significantly reduced computation time for large-scale problems.

Faster convergence demonstrated on multiple neural network benchmarks.

Abstract

Swarm intelligence optimization algorithms have gained significant attention due to their ability to solve complex optimization problems. However, the efficiency of optimization in large-scale problems limits the use of related methods. This paper presents a GPU-accelerated version of the Multi-Guiding Spark Fireworks Algorithm (MGFWA), which significantly improves the computational efficiency compared to its traditional CPU-based counterpart. We benchmark the GPU-MGFWA on several neural network black-box optimization problems and demonstrate its superior performance in terms of both speed and solution quality. By leveraging the parallel processing power of modern GPUs, the proposed GPU-MGFWA results in faster convergence and reduced computation time for large-scale optimization tasks. The proposed implementation offers a promising approach to accelerate swarm intelligence algorithms, making them more suitable for real-time applications and large-scale industrial problems. Source code is released at https://github.com/mxxxr/MGFWA.