Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling

arXiv:2607.15682 · cs.LG, cond-mat.stat-mech, hep-lat · Submitted 2026-07-17 · Read on arXiv

cs.LG, cond-mat.stat-mech, hep-lat

Submitted: 2026-07-17

Updated: 2026-08-26

Code: https://github.com/qxxmax/lattice-ml

Terminology

• Normalizing Flow — 9× in this paper · explained in 3 episodes
• Normalizing Flows — 9× in this paper · explained in 4 episodes
• Trace — 8× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Flow Matching — 4× in this paper · explained in 8 episodes
• Sample Efficiency — 4× in this paper · explained in 4 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Neural Non-Equilibrium Hamiltonian Monte Carlo — 3× in this paper
• Degeneracy — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Training — 1× in this paper · explained in 1 episode
• Computational Biology — 1× in this paper · explained in 2 episodes
• Diffusion Processes — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Online Adaptation — 1× in this paper · explained in 3 episodes

Sources

• Normalizing flows for lattice gauge theory in arbitrary space-time dimension
• BoltzNCE: Learning Likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation
• Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
• NETS: A Non-Equilibrium Transport Sampler
• Annealed Flow Transport Monte Carlo
• Markov Chain Monte Carlo with Diffusion Paths
• Stochastic Path Sampler For Lattice Field Theory
• Counterdiabatic Hamiltonian Monte Carlo
• The Entropy Production Fluctuation Theorem and the Nonequilibrium Work Relation for Free Energy Differences
• Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
• Deep Learning Hamiltonian Monte Carlo
• Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
• Training Neural Samplers with Reverse Diffusive KL Divergence
• Generalizing Hamiltonian Monte Carlo with Neural Networks
• Continual Repeated Annealed Flow Transport Monte Carlo
• Flow Annealed Importance Sampling Bootstrap
• BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching
• Hamiltonian Annealed Importance Sampling for partition function estimation
• A-NICE-MC: Adversarial Training for MCMC
• Scalable Equilibrium Sampling with Sequential Boltzmann Generators

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks