BADM: Batch ADMM for Deep Learning

2024/06/30 by Ouya Wang, Shenglong Zhou, Wang, Ouya +3 · 1 citation
Computer Science · Neuroscience · #Brain Tumor Detection and Classification #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2407.01640

openalex publication_date 2024/06/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers (ADMM) to develop a novel data-driven algorithm, called batch ADMM (BADM). The fundamental idea of the proposed algorithm is to split the training data into batches, which is further divided into sub-batches where primal and dual variables are updated to generate global parameters through aggregation. We evaluate the performance of BADM across various deep learning tasks, including graph modelling, computer vision, image generation, and natural language processing. Extensive numerical experiments demonstrate that BADM achieves faster convergence and superior testing accuracy compared to other state-of-the-art optimizers.

Cited by

• Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes

Related

• AA-DLADMM: An Accelerated ADMM-based Framework for Training Deep Neural Networks
• A Convergent ADMM Framework for Efficient Neural Network Training
• Stochastic Block-ADMM for Training Deep Networks
• Toward Model Parallelism for Deep Neural Network based on Gradient-free ADMM Framework
• DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation