Diabatic quantum annealing for training energy-based generative models

Abstract

Energy-based generative models, such as restricted Boltzmann machines (RBMs), require unbiased Boltzmann samples for effective training. Classical Markov chain Monte Carlo methods, however, converge slowly and yield correlated samples, making large-scale training difficult. We address this bottleneck by applying the analytic relation between annealing schedules and effective inverse temperature in diabatic quantum annealing. By implementing this prescription on a quantum annealer, we obtain temperature-controlled Boltzmann samples that enable RBM training with faster convergence and lower validation error than classical sampling. We further identify a systematic temperature misalignment intrinsic to analog quantum computers and propose an analytical rescaling method that mitigates this hardware noise, thereby enhancing the practicality of quantum annealers as Boltzmann samplers. In our method, the model's connectivity is set directly by the qubit connectivity, transforming the computational complexity inherent in classical sampling into a requirement on quantum hardware. This shift allows the approach to extend naturally from RBMs to fully connected Boltzmann machines, opening opportunities inaccessible to classical training methods.

10 pages, 9 figures

References in corpus (16)

• Surface codes: Towards practical large-scale quantum computation
• Quantum Annealing in the Transverse Ising Model
• Error mitigation for short-depth quantum circuits
• Quantum Error Correction for Quantum Memories
• Practical Quantum Error Mitigation for Near-Future Applications
• Quantum computing with neutral atoms
• Mitigating measurement errors in multi-qubit experiments
• Observation of topological phenomena in a programmable lattice of 1,800 qubits
• Quantum critical dynamics in a 5000-qubit programmable spin glass
• Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
• Searching for quantum speedup in quasistatic quantum annealers
• Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Q
• Training a quantum annealing based restricted Boltzmann machine on cybersecurity data
• Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning
• Scalable quantum measurement error mitigation via conditional independence and transfer learning
• Classical Criticality via Quantum Annealing