Training Neural Networks with Universal Adiabatic Quantum Computing
This addresses the resource-heavy training process for neural networks, offering a potential alternative, though it appears incremental as it adapts AQC to a known bottleneck.
The paper tackled the computationally intensive problem of training neural networks by using Adiabatic Quantum Computing (AQC) to find the global minimum of the loss function, with results indicating very efficient performance across networks with continuous, discrete, and binary weights.
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.