Quantum Annealing Formulation for Binary Neural Networks

Abstract

Quantum annealing is a promising paradigm for building practical quantum computers. Compared to other approaches, quantum annealing technology has been scaled up to a larger number of qubits. On the other hand, deep learning has been profoundly successful in pushing the boundaries of AI. It is thus natural to investigate potentially game changing technologies such as quantum annealers to augment the capabilities of deep learning. In this work, we explore binary neural networks, which are lightweight yet powerful models typically intended for resource constrained devices. Departing from current training regimes for binary networks that smooth/approximate the activation functions to make the network differentiable, we devise a quadratic unconstrained binary optimization formulation for the training problem. While the problem is intractable, i.e., the cost to estimate the binary weights scales exponentially with network size, we show how the problem can be optimized directly on a quantum annealer, thereby opening up to the potential gains of quantum computing. We experimentally validated our formulation via simulation and testing on an actual quantum annealer (D-Wave Advantage), the latter to the extent allowable by the capacity of current technology.

arXiv comment13 pages, 4 figures

References in corpus (17)

• Quantum Machine Learning
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Efficient Learning for Deep Quantum Neural Networks
• The quest for a Quantum Neural Network
• Binary Neural Networks: A Survey
• Experimental Investigation of an Eight Qubit Unit Cell in a Superconducting Optimization Processor
• A practical heuristic for finding graph minors
• Support vector machines on the D-Wave quantum annealer
• A Tutorial on Formulating and Using QUBO Models
• XNOR Neural Engine: a Hardware Accelerator IP for 21.6 fJ/op Binary Neural Network Inference
• XNOR-Net++: Improved Binary Neural Networks
• Prediction and real-time compensation of qubit decoherence via machine-learning
• Adiabatic Quantum Linear Regression
• Training a Binary Classifier with the Quantum Adiabatic Algorithm
• Scrambling Ability of Quantum Neural Networks Architectures
• A QUBO Model for Gaussian Process Variance Reduction