Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM

TL;DR

This paper introduces a novel ADMM-based method for training extremely low bit neural networks, significantly improving efficiency and accuracy in model compression for resource-constrained environments.

Contribution

It proposes a new optimization framework using ADMM and specialized algorithms to effectively train neural networks with very low bit weights, outperforming existing methods.

Findings

Outperforms state-of-the-art low bit neural network methods.

Achieves faster convergence with extragradient and iterative quantization algorithms.

Effective in image recognition and object detection tasks.

Abstract

Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on compressing and accelerating deep models with network weights represented by very small numbers of bits, referred to as extremely low bit neural network. We model this problem as a discretely constrained optimization problem. Borrowing the idea from Alternating Direction Method of Multipliers (ADMM), we decouple the continuous parameters from the discrete constraints of network, and cast the original hard problem into several subproblems. We propose to solve these subproblems using extragradient and iterative quantization algorithms that lead to considerably faster convergency compared to conventional optimization methods. Extensive experiments on image recognition and object detection verify that the proposed algorithm is more effective than state-of-the-art approaches when coming to extremely low bit neural network.