Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing

TL;DR

This paper investigates the use of adiabatic quantum computing (AQC) for neural network compression, reformulating model pruning as a QUBO problem and demonstrating AQC's efficiency and effectiveness over classical methods.

Contribution

It introduces a novel reformulation of neural network compression as a QUBO problem suitable for AQC and evaluates its performance on practical DNN models.

Findings

AQC achieves effective model compression.

AQC outperforms classical algorithms in time efficiency.

AQC excels at finding global optima.

Abstract

Quantum optimization is the most mature quantum computing technology to date, providing a promising approach towards efficiently solving complex combinatorial problems. Methods such as adiabatic quantum computing (AQC) have been employed in recent years on important optimization problems across various domains. In deep learning, deep neural networks (DNN) have reached immense sizes to support new predictive capabilities. Optimization of large-scale models is critical for sustainable deployment, but becomes increasingly challenging with ever-growing model sizes and complexity. While quantum optimization is suitable for solving complex problems, its application to DNN optimization is not straightforward, requiring thorough reformulation for compatibility with commercially available quantum devices. In this work, we explore the potential of adopting AQC for fine-grained pruning-quantization of convolutional neural networks. We rework established heuristics to formulate model compression as a quadratic unconstrained binary optimization (QUBO) problem, and assess the solution space offered by commercial quantum annealing devices. Through our exploratory efforts of reformulation, we demonstrate that AQC can achieve effective compression of practical DNN models. Experiments demonstrate that adiabatic quantum computing (AQC) not only outperforms classical algorithms like genetic algorithms and reinforcement learning in terms of time efficiency but also excels at identifying global optima.