Online calibration scheme for training restricted Boltzmann machines with quantum annealing
arXiv:2307.09785 · doi:10.7566/JPSJ.94.034002
Abstract
We propose a scheme to calibrate the internal parameters of a quantum annealer to obtain well-approximated samples for training a restricted Boltzmann machine (RBM). Empirically, samples from quantum annealers obey the Boltzmann distribution, making them suitable for RBM training. Quantum annealers utilize physical phenomena to generate a large number of samples in a short time. However, hardware imperfections make it challenging to obtain accurate samples. Existing research often estimates the inverse temperature for the compensation. Our scheme efficiently utilizes samples for RBM training also to estimate internal parameters. Furthermore, we consider additional parameters and demonstrate that they improve sample quality. We evaluate our approach by comparing the obtained samples with classical Gibbs sampling, which theoretically generates accurate samples. Our results indicate that our scheme demonstrates performance on par with Gibbs sampling. In addition, the training results with our estimation scheme outperform those of the contrastive divergence algorithm, a standard training algorithm for RBM.
17 pages, 6 figures, 1 table
References in corpus (10)
- Coherent quantum annealing in a programmable 2000-qubit Ising chain
- Quantum Annealing for Combinatorial Clustering
- Benchmark of quantum-inspired heuristic solvers for quadratic unconstrained binary optimization
- Item Listing Optimization for E-commerce Websites based on Diversity
- Travel time optimization on multi-AGV routing by reverse annealing
- Benchmark test of Black-box optimization using D-Wave quantum annealer
- Simulated quantum annealing as a simulator of non-equilibrium quantum dynamics
- Fair Sampling by Simulated Annealing on Quantum Annealer
- Comparing the effects of Boltzmann machines as associative memory in Generative Adversarial Networks between classical and quantum sampling
- Virtual Screening of Chemical Space based on Quantum Annealing