Approximate stochastic localization plus conductance transfers yield a weak Poincaré inequality for the SK model at β < 1/2, enabling efficient Glauber sampling from a warm start.
arXiv preprint arXiv:2410.02711 , year =
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
abstract
We propose an algorithm, termed the Non-Equilibrium Transport Sampler (NETS), to sample from unnormalized probability distributions. NETS can be viewed as a variant of annealed importance sampling (AIS) based on Jarzynski's equality, in which the stochastic differential equation used to perform the non-equilibrium sampling is augmented with an additional learned drift term that lowers the impact of the unbiasing weights used in AIS. We show that this drift is the minimizer of a variety of objective functions, which can all be estimated in an unbiased fashion without backpropagating through solutions of the stochastic differential equations governing the sampling. We also prove that some these objectives control the Kullback-Leibler divergence of the estimated distribution from its target. NETS is shown to be unbiased and, in addition, has a tunable diffusion coefficient which can be adjusted post-training to maximize the effective sample size. We demonstrate the efficacy of the method on standard benchmarks, high-dimensional Gaussian mixture distributions, and a model from statistical lattice field theory, for which it surpasses the performances of related work and existing baselines.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
Generalizes neural transport methods for free energy estimation to any state space with added algebraic and group-theoretic results on time reversal and h-transforms.
A unified framework decomposes Wasserstein gradient flow velocity fields across f-divergences into a shared beta direction and divergence-specific weighting, enabling data-free one-step sampling.
Polynomial-time algorithm samples the Sherrington-Kirkpatrick Gibbs measure at beta < 1/2 with o(1) TVD error by combining potential Hessian ascent, stochastic localization, covariance estimates, and Jarzynski equality with rejection sampling.
Functional tensor trains plus BSDE regression solve the HJB score PDE, yielding a fast low-rank sampler that outperforms neural diffusion methods on multimodal targets.
SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.
SURGE is an unbiased particle filter that fuses diffusion-model simulations with noisy observations via sequential Monte Carlo reweighting over diffusion trajectories.
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
Geometric tempering yields exponential convergence bounds for both Wasserstein and Fisher-Rao flows but produces no speedup in the Fisher-Rao metric, with new adaptive schedules derived from the tempered dynamics.
Out-of-equilibrium simulations with open-to-periodic boundary switching plus a tailored stochastic normalizing flow enable efficient topology sampling in the continuum limit of four-dimensional SU(3) Yang-Mills theory.
Energy-Weighted Flow Matching reformulates conditional flow matching with importance sampling to enable continuous normalizing flows to model Boltzmann distributions from energy evaluations alone, with iterative and annealed variants showing competitive performance on benchmarks.
Generative models learn conditional local distributions conditioned on neighbors and action parameters to improve Heatbath proposals for continuous-variable lattice models without target samples.
citing papers explorer
-
Weak Poincar\'e Inequalities via Approximate Stochastic Localization: Application to Sampling the Sherrington-Kirkpatrick Model
Approximate stochastic localization plus conductance transfers yield a weak Poincaré inequality for the SK model at β < 1/2, enabling efficient Glauber sampling from a warm start.
-
Adaptive Order Policies for Masked Diffusion
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
-
Free energy Estimation on Any State Space
Generalizes neural transport methods for free energy estimation to any state space with added algebraic and group-theoretic results on time reversal and h-transforms.
-
A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows
A unified framework decomposes Wasserstein gradient flow velocity fields across f-divergences into a shared beta direction and divergence-specific weighting, enabling data-free one-step sampling.
-
Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2
Polynomial-time algorithm samples the Sherrington-Kirkpatrick Gibbs measure at beta < 1/2 with o(1) TVD error by combining potential Hessian ascent, stochastic localization, covariance estimates, and Jarzynski equality with rejection sampling.
-
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
Functional tensor trains plus BSDE regression solve the HJB score PDE, yielding a fast low-rank sampler that outperforms neural diffusion methods on multimodal targets.
-
Scalable Inference-Time Annealing with Surrogate Likelihood Estimators
SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.
-
SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate
SURGE is an unbiased particle filter that fuses diffusion-model simulations with noisy observations via sequential Monte Carlo reweighting over diffusion trajectories.
-
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
-
Properties and limitations of geometric tempering for gradient flow dynamics
Geometric tempering yields exponential convergence bounds for both Wasserstein and Fisher-Rao flows but produces no speedup in the Fisher-Rao metric, with new adaptive schedules derived from the tempered dynamics.
-
Scaling flow-based approaches for topology sampling in $\mathrm{SU}(3)$ gauge theory
Out-of-equilibrium simulations with open-to-periodic boundary switching plus a tailored stochastic normalizing flow enable efficient topology sampling in the continuum limit of four-dimensional SU(3) Yang-Mills theory.
-
Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
Energy-Weighted Flow Matching reformulates conditional flow matching with importance sampling to enable continuous normalizing flows to model Boltzmann distributions from energy evaluations alone, with iterative and annealed variants showing competitive performance on benchmarks.
-
Improvement of Heatbath Algorithm in LFT using Generative models
Generative models learn conditional local distributions conditioned on neighbors and action parameters to improve Heatbath proposals for continuous-variable lattice models without target samples.