BADM: Batch ADMM for Deep Learning

TL;DR

BADM is a novel batch ADMM algorithm for deep learning that improves convergence speed and accuracy by dividing data into sub-batches and updating variables iteratively, outperforming traditional optimizers.

Contribution

The paper introduces BADM, a new ADMM-based training algorithm that enhances deep learning optimization by leveraging batch and sub-batch data division.

Findings

Faster convergence than existing optimizers

Superior testing accuracy across tasks

Effective in various deep learning applications

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.