Training Neural Networks with Universal Adiabatic Quantum Computing

TL;DR

This paper introduces a universal adiabatic quantum computing approach for training neural networks, leveraging quantum principles to efficiently find global minima and potentially outperform classical methods.

Contribution

It presents a novel universal AQC method compatible with gate quantum computers for training diverse neural networks, expanding quantum applications in machine learning.

Findings

AQC efficiently finds global minima of neural network loss functions.

The method applies to networks with continuous, discrete, and binary weights.

Results suggest AQC as a promising alternative to classical training algorithms.

Abstract

The training of neural networks (NNs) is a computationally intensive task requiring significant time and resources. This paper presents a novel approach to NN training using Adiabatic Quantum Computing (AQC), a paradigm that leverages the principles of adiabatic evolution to solve optimisation problems. We propose a universal AQC method that can be implemented on gate quantum computers, allowing for a broad range of Hamiltonians and thus enabling the training of expressive neural networks. We apply this approach to various neural networks with continuous, discrete, and binary weights. Our results indicate that AQC can very efficiently find the global minimum of the loss function, offering a promising alternative to classical training methods.