Jeffreys Flow: Robust Boltzmann Generators for Rare Event Sampling via Parallel Tempering Distillation

• URL: http://arxiv.org/abs/2604.05303v1
• Date: Tue, 07 Apr 2026 01:17:53 GMT
• Title: Jeffreys Flow: Robust Boltzmann Generators for Rare Event Sampling via Parallel Tempering Distillation
• Abstract summary: Boltzmann generators rely on the reverse Kullback--bler divergence to Sampling physical systems with rough energy is hindered by rare events and metastable trapping.<n>We introduce Jeffreys Flow, a robust generative framework that mitigates this failure.
• Score: 9.242166517719111
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sampling physical systems with rough energy landscapes is hindered by rare events and metastable trapping. While Boltzmann generators already offer a solution, their reliance on the reverse Kullback--Leibler divergence frequently induces catastrophic mode collapse, missing specific modes in multi-modal distributions. Here, we introduce the Jeffreys Flow, a robust generative framework that mitigates this failure by distilling empirical sampling data from Parallel Tempering trajectories using the symmetric Jeffreys divergence. This formulation effectively balances local target-seeking precision with global modes coverage. We show that minimizing Jeffreys divergence suppresses mode collapse and structurally corrects inherent inaccuracies via distillation of the empirical reference data. We demonstrate the framework's scalability and accuracy on highly non-convex multidimensional benchmarks, including the systematic correction of stochastic gradient biases in Replica Exchange Stochastic Gradient Langevin Dynamics and the massive acceleration of exact importance sampling in Path Integral Monte Carlo for quantum thermal states.

Related papers

• Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting [57.75750707482832]
  We introduce variance-corrective time shifting, a training-free fix that queries the network at a shifted timestep and scales the resulting score by $$, canceling the variance inflation while preserving the mode reweighting.<n>We demonstrate consistent gains at minimal cost to sample quality and condition fidelity across DiT, Stable Diffusion and Motion Diffusion models.
  arXiv  Detail & Related papers  (2026-07-12T17:32:29Z)
• Demystifying Variance in Circuit Discovery of LLMs [51.97489679448601]
  We develop a new circuit discovery method that substantially lessens resampling variance.<n>We show that rephrasing variance arises because prompts with different templates tend to activate different circuits in the model.<n>We argue that sparsity, which has been claimed to form more compact and interpretable task circuits, fails to solve this problem.
  arXiv  Detail & Related papers  (2026-06-15T16:25:07Z)
• Probability-Conserving Flow Guidance [49.03107678763765]
  Adaptive Manifold Guidance (AdaMaG) improves realism, reduces hallucinations, and controlled desaturation in high-guidance.<n>Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and controlled desaturation in high-guidance.
  arXiv  Detail & Related papers  (2026-05-19T16:34:01Z)
• PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting [62.22445401483844]
  Existing methods are severely constrained by the bottleneck of compounding errors.<n>We propose a universal framework called -Cast-Corrector (Plug-and-Play Corrector)<n>Our method significantly enhances the long-term stability of coupled forecasting systems.
  arXiv  Detail & Related papers  (2026-05-09T13:12:33Z)
• Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures [12.937511747845436]
  We provide a mathematical analysis of strategies for mitigating mode collapse in a tractable setting.<n>Our analysis shows that an appropriately chosen annealing scheme can robustly prevent mode collapse.<n>We present numerical evidence that these theoretical tradeoffs qualitatively extend to neural network based models, RealNVP normalizing flows.
  arXiv  Detail & Related papers  (2026-02-13T13:28:23Z)
• Coarse-Grained Boltzmann Generators [2.8880597165704]
  We propose a principled framework that unifies scalable reduced-order modeling with the exactness of importance sampling.<n>CG-BGs act in a coarse-grained coordinate space, using a learned potential of mean force to reweight samples generated by a flow-based model.<n>Our results demonstrate that CG-BGs faithfully capture complex interactions mediated by explicit solvent within highly reduced representations.
  arXiv  Detail & Related papers  (2026-02-11T08:37:13Z)
• A scalable flow-based approach to mitigate topological freezing [34.54607280864912]
  We present a flow-based strategy to remove topological artifacts from Markov Chain Monte Carlo simulations.<n>The strategy is based on a Normalizing Flow (SNF) that alternates non-equilibrium Monte Carlo updates with localized, stout-equivariant defect layers.<n>We show that defect SNFs achieve better performances than reproducing non-equilibrium methods at comparable cost.
  arXiv  Detail & Related papers  (2026-01-28T15:40:46Z)
• Entropy-Reservoir Bregman Projection: An Information-Geometric Unification of Model Collapse [3.533187668612022]
  We present EntropyReser Bregman Projection- ERBP, an information-geometric framework that unifies these phenomena.<n>Our theory yields a necessary condition for collapse, (ii) a sufficient condition that guarantees a non-language entropy floor, and (iii) closed-form rates that depend on sample size.
  arXiv  Detail & Related papers  (2025-12-16T19:50:03Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• 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)
• Scalable Equilibrium Sampling with Sequential Boltzmann Generators [60.00515282300297]
  We extend the Boltzmann generator framework with two key contributions.<n>The first is a highly efficient Transformer-based normalizing flow operating directly on all-atom Cartesian coordinates.<n>In particular, we perform inference-time scaling of flow samples using a continuous-time variant of sequential Monte Carlo.
  arXiv  Detail & Related papers  (2025-02-25T18:59:13Z)
• Temperature-Annealed Boltzmann Generators [0.6906005491572401]
  Training a normalizing flow with the reverse Kullback-Leibler divergence at high temperatures is possible without mode collapse.<n>We introduce a reweighting-based training objective to anneal the distribution to lower target temperatures.<n>For the largest system, our approach is the only method that accurately resolves the metastable states of the system.
  arXiv  Detail & Related papers  (2025-01-31T12:09:40Z)
• Predicting Cascading Failures with a Hyperparametric Diffusion Model [66.89499978864741]
  We study cascading failures in power grids through the lens of diffusion models. Our model integrates viral diffusion principles with physics-based concepts. We show that this diffusion model can be learned from traces of cascading failures.
  arXiv  Detail & Related papers  (2024-06-12T02:34:24Z)
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue [95.23775347605923]
  Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples. GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution. We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
  arXiv  Detail & Related papers  (2020-09-24T19:34:37Z)

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.