EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation

Kentaro Kubo, Hayato Goto

PRX Intelligence · 2026

DOI: 10.1103/2vb5-2lt8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PRX Intelligence, 2026. Verfasst von Kentaro Kubo und 1 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Kubo, K., & Goto, H. (2026). Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation. PRX Intelligence. https://doi.org/10.1103/2vb5-2lt8

Vancouver

Kubo K, Goto H. Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation. PRX Intelligence. 2026. doi:10.1103/2vb5-2lt8

BibTeX
@article{Kubo2026,
  author = {Kubo, Kentaro and Goto, Hayato},
  title = {Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation},
  journal = {PRX Intelligence},
  year = {2026},
  doi = {10.1103/2vb5-2lt8}
}
Kostenlos starten →