Optimising functions with Quantum Annealers
No Thumbnail Available
URL
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
Master's thesis
Authors
Date
2024-03-11
Department
Major/Subject
Machine Learning, Data Science and Artificial Intelligence
Mcode
SCI3044
Degree programme
Master’s Programme in Computer, Communication and Information Sciences
Language
en
Pages
46+2
Series
Abstract
We present, QP-SBGD, a novel layer-wise stochastic optimizer tailored towards training neural networks with binary weights, known as binary neural networks (BNNs), on quantum hardware. BNNs reduce the computational requirements and energy consumption of deep learning models without compromising accuracy. However, training them in practice remains to be an open challenge. Most known BNN-optimizers either rely on projected updates or binarize weights post-training. Instead, QP-SBGD approximately projects the gradient onto binary variables, by solving a quadratic constrained binary optimization. Under empirically validated √ assumptions, we show that this update rule converges with a rate of O(1/ T). Moreover, we show how the NP-hard projection can be effectively executed on an adiabatic quantum annealer, harnessing recent advancements in quantum computation. We also introduce a binary projected version of this update rule and prove that if a fixed point exists in the binary variable space, the modified updates will converge to it. Last but not least, our algorithm is implemented layer-wise, making it suitable to train larger networks on resource-limited quantum hardware. Through extensive evaluations, we show that QP-SBGD outperforms or is on par with competitive and well-established baselines such as BinaryConnect, signSGD and ProxQuant when optimizing the Rosenbrock function and training various neural network setups.Description
Supervisor
Kannala, JuhoThesis advisor
Birdal, TolgaGolyanik, Vladislav
Keywords
optimisation, computer vision, quantum computing, machine learning