Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation
Open Access
- 17 September 2026
- journal article
- research article
- Published by American Physical Society (APS) in PRX Intelligence
- Vol. 1 (1) , 013021
Abstract
Efficient sampling from Boltzmann distributions over discrete variables is a fundamental operation in a wide range of applications. While fast non-Markov chain Monte Carlo (MCMC) samplers have recently emerged as promising alternatives to conventional MCMC methods, their practical use for probabilistic learning remains hindered by the difficulty of estimating the effective temperature of the generated samples. In this work, we begin by introducing Langevin simulated bifurcation (LSB), a Boltzmann sampler that enables fast and parallel sampling with accuracy comparable to sequential MCMC methods. To address the challenge of unknown effective temperature, we propose conditional expectation matching (CEM), an efficient estimation method applicable to energy-based models (EBMs) with exploitable conditional independence structures. Building on these components, we further develop a learning framework, termed sampler adaptive learning (SAL), which adaptively adjusts the model temperature to match that of the distribution induced by fast non-MCMC sampling. We demonstrate the effectiveness of LSB, CEM, and SAL on semirestricted Boltzmann machines (SRBMs), a class of EBMs that are difficult to train using conventional approaches. LSB achieves orders-of-magnitude acceleration over Gibbs sampling while maintaining comparable or higher accuracy, and CEM enables accurate temperature estimation of the resulting distribution with negligible computational overhead. As a consequence, SAL enables efficient training of SRBMs and outperforms conventional Boltzmann machine learning methods on synthetic spin-glass datasets. In addition, the trained models achieve strong performance across multiple tasks, including image generation, reconstruction, and classification. These results establish LSB as a fast and accurate Boltzmann sampler and provide key insights that enable practical applications of fast non-MCMC sampling methods via efficient temperature estimation with CEM.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learningNature Communications, 2022
- Simulated bifurcation assisted by thermal fluctuationCommunications Physics, 2022
- Assessment of image generation by quantum annealerScientific Reports, 2021
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Boltzmann sampling from the Ising model using quantum heating of coupled nonlinear oscillatorsScientific Reports, 2018
- Quantum annealing with manufactured spinsNature, 2011
- An Introduction to MCMC for Machine LearningMachine Learning, 2003
- Langevin Diffusions and Metropolis-Hastings AlgorithmsMethodology and Computing in Applied Probability, 2002
- A learning algorithm for boltzmann machinesCognitive Science, 1985
- Equation of State Calculations by Fast Computing MachinesThe Journal of Chemical Physics, 1953