Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

• URL: http://arxiv.org/abs/2607.27077v1
• Date: Wed, 29 Jul 2026 16:00:59 GMT
• Title: Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
• Abstract summary: Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data.<n>We introduce a training algorithm based on Parallel Trajectory Tempering (PTT)<n>PTT exploits the continuity of the optimization path to maintain equilibrium sampling throughout learning.
• Score: 11.614569891383873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability. We introduce a training algorithm based on Parallel Trajectory Tempering (PTT), which exploits the continuity of the optimization path to maintain equilibrium sampling throughout learning. This enables stable and fast training on highly multimodal and data-scarce scientific datasets. Combined with reservoir sampling and adaptive optimization, PTT has a computational cost comparable to Persistent Contrastive Divergence, making it a practical replacement for standard training methods. It also provides direct estimates of thermalization times, equilibrium samples from trained models, and accurate log-likelihoods at essentially no additional cost. Experiments on Restricted Boltzmann Machines show that PTT consistently outperforms existing EBM training approaches. On discrete tabular data, it also surpasses state-of-the-art deep generative models, yielding higher-quality samples and greater robustness to overfitting and limited data. Our results make equilibrium maximum-likelihood training of EBMs practical and computationally efficient.

Related papers

• FALCON: Few-step Accurate Likelihoods for Continuous Flows [78.37361800856583]
  We propose Few-step Accurate Likelihoods for Continuous Flows (FALCON), which allows for few-step sampling with a likelihood accurate enough for importance sampling applications.<n>We show FALCON outperforms state-of-the-art normalizing flow models for molecular Boltzmann sampling and is two orders of magnitude faster than the equivalently performing CNF model.
  arXiv  Detail & Related papers  (2025-12-10T18:47:25Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Fast training and sampling of Restricted Boltzmann Machines [4.785158987724452]
  We build upon recent theoretical advancements in RBM training, to significantly reduce the computational cost of training. We propose a pre-training phase that encodes the principal components into a low-rank RBM through a convex optimization process. We exploit the continuous and smooth nature of the parameter annealing trajectory to achieve reliable and computationally efficient log-likelihood estimations.
  arXiv  Detail & Related papers  (2024-05-24T09:23:43Z)
• Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann Estimators [11.699834591020057]
  We present Stability-Aware Boltzmann Estimator (StABlE) Training, a multi-modal training procedure for machine learning force fields.<n>StABlE Training iteratively runs MD simulations in parallel to seek out unstable regions, and corrects the instabilities via supervision.<n>We demonstrate our methodology across organic molecules, tetrapeptides, and condensed phase systems.
  arXiv  Detail & Related papers  (2024-02-21T18:12:07Z)
• Online Variational Sequential Monte Carlo [49.97673761305336]
  We build upon the variational sequential Monte Carlo (VSMC) method, which provides computationally efficient and accurate model parameter estimation and Bayesian latent-state inference. Online VSMC is capable of performing efficiently, entirely on-the-fly, both parameter estimation and particle proposal adaptation.
  arXiv  Detail & Related papers  (2023-12-19T21:45:38Z)
• Learning Energy-Based Prior Model with Diffusion-Amortized MCMC [89.95629196907082]
  Common practice of learning latent space EBMs with non-convergent short-run MCMC for prior and posterior sampling is hindering the model from further progress. We introduce a simple but effective diffusion-based amortization method for long-run MCMC sampling and develop a novel learning algorithm for the latent space EBM based on it.
  arXiv  Detail & Related papers  (2023-10-05T00:23:34Z)
• Balanced Training of Energy-Based Models with Adaptive Flow Sampling [13.951904929884618]
  Energy-based models (EBMs) are versatile density estimation models that directly parameterize an unnormalized log density. We propose a new maximum likelihood training algorithm for EBMs that uses a different type of generative model, normalizing flows (NF) Our method fits an NF to an EBM during training so that an NF-assisted sampling scheme provides an accurate gradient for the EBMs at all times.
  arXiv  Detail & Related papers  (2023-06-01T13:58:06Z)
• Stabilizing Machine Learning Prediction of Dynamics: Noise and Noise-inspired Regularization [58.720142291102135]
  Recent has shown that machine learning (ML) models can be trained to accurately forecast the dynamics of chaotic dynamical systems. In the absence of mitigating techniques, this technique can result in artificially rapid error growth, leading to inaccurate predictions and/or climate instability. We introduce Linearized Multi-Noise Training (LMNT), a regularization technique that deterministically approximates the effect of many small, independent noise realizations added to the model input during training.
  arXiv  Detail & Related papers  (2022-11-09T23:40:52Z)
• Learning a Restricted Boltzmann Machine using biased Monte Carlo sampling [0.6554326244334867]
  We show that sampling the equilibrium distribution via Markov Chain Monte Carlo can be dramatically accelerated using biased sampling techniques. We also show that this sampling technique can be exploited to improve the computation of the log-likelihood gradient during the training too.
  arXiv  Detail & Related papers  (2022-06-02T21:29:01Z)
• No MCMC for me: Amortized sampling for fast and stable training of energy-based models [62.1234885852552]
  Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty. We present a simple method for training EBMs at scale using an entropy-regularized generator to amortize the MCMC sampling. Next, we apply our estimator to the recently proposed Joint Energy Model (JEM), where we match the original performance with faster and stable training.
  arXiv  Detail & Related papers  (2020-10-08T19:17:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.