Pith. sign in

REVIEW 12 cited by

NETS: A Non-Equilibrium Transport Sampler

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.02711 v3 pith:FDMKUMDC submitted 2024-10-03 cs.LG cond-mat.stat-mechhep-lat

Michael S. Albergo , Eric Vanden-Eijnden This is my paper · ORCID
classification cs.LGcond-mat.stat-mechhep-lat
keywords netsnon-equilibriumsamplingdifferentialdistributionsdriftestimatedsample
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Weak Poincar\'e Inequalities via Approximate Stochastic Localization: Application to Sampling the Sherrington-Kirkpatrick Model

    math.PR 2026-07 conditional novelty 7.0 of 10

    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.

  2. Stochastic Quantization as Optimal Control

    hep-lat 2026-07 conditional novelty 6.0 of 10

    Stochastic quantization is re-expressed as finite-time optimal control, in which a learned Doob force plus exact path weights reach the Gibbs measure without waiting for equilibrium.

  3. Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling

    stat.ML 2026-07 accept novelty 6.0 of 10

    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.

  4. Machine-Learned Sampling of Conditioned Path Measures

    stat.ML 2025-06 conditional novelty 6.0 of 10

    Two new algorithm families (controlled transport on path space and Wasserstein/JKO density evolution) for sampling posterior path measures without trajectory data, with theoretical consistency equations and toy experiments.

  5. No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Simulation-free training of neural samplers fails without Langevin preconditioning, and parallel tempering followed by fitting a diffusion model is a stronger baseline than most neural samplers.

  6. Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo

    cs.LG 2025-02 conditional novelty 6.0 of 10

    An SMC importance-sampling algorithm debiases discrete diffusion guidance, asymptotically sampling from the target tempered distribution p0(x0)p(ζ|x0)^α.

  7. Stochastic Counterdiabatic Driving via Biorthogonal Liouvillian Eigenmodes

    physics.comp-ph 2026-07 conditional novelty 5.0 of 10

    Biorthogonal eigenmodes of the discrete Fokker–Planck generator yield a counterdiabatic correction that tracks instantaneous equilibrium to machine precision and drives dissipated work to ~0 at arbitrary protocol speed.

  8. Continuously Tempered Diffusion Samplers

    cs.LG 2025-08 conditional novelty 5.0 of 10

    CTDS trains neural samplers with a controlled Langevin dynamics over both position and a continuous temperature coordinate, and reports improved sampling on a 40-mode Gaussian mixture.

  9. Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework

    cs.HC 2025-08 unverdicted novelty 5.0 of 10

    A three-layer framework (input, processing, output) for adaptive external human-machine interfaces in autonomous vehicles is introduced to systematize design and analysis.

  10. Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.

  11. Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Importance Weighted Score Matching trains diffusion samplers by reweighting score matching with self-normalized importance sampling to approximate the forward KL and improve mode coverage.

  12. Neural Flow Samplers with Shortcut Models

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Neural Flow Shortcut Sampler (NFS2) estimates the partition-function derivative with velocity-driven SMC and Stein control variates, and adds a generalized shortcut consistency loss for few-step sampling.

Pith tools