Pith. sign in

REVIEW 3 cited by

Hamiltonian Annealed Importance Sampling for partition function estimation

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 1205.1925 v1 pith:RE54BUSZ submitted 2012-05-09 cs.LG physics.data-an

Jascha Sohl-Dickstein , Benjamin J. Culpepper This is my paper · ORCID
classification cs.LGphysics.data-an
keywords modelsannealedcompareexpertsgenerativehamiltonianimportancelaplace
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce an extension to annealed importance sampling that uses Hamiltonian dynamics to rapidly estimate normalization constants. We demonstrate this method by computing log likelihoods in directed and undirected probabilistic image models. We compare the performance of linear generative models with both Gaussian and Laplace priors, product of experts models with Laplace and Student's t experts, the mc-RBM, and a bilinear generative model. We provide code to compare additional models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond

    stat.ML 2025-02 unverdicted novelty 7.0 of 10

    Derives Õ(d β² A² / ε⁴) oracle complexity for AIS estimating normalizing constant Z to relative error ε and introduces reverse diffusion sampler for geometric paths with large action.

  2. Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A train-then-correct Hamiltonian Monte Carlo with learned stochastic paths gives exact Boltzmann corrections via a recorded generalized work, with limited but honest empirical validation.

  3. Quantum Computing for Partition Function Estimation of a Markov Random Field in a Radar Anomaly Detection Problem

    cs.ET 2025-01 conditional novelty 3.0 of 10

    Simulations show a one-clean-qubit algorithm estimates partition functions of small binary Markov random fields, with errors matching the expected sample-size trend.

Pith tools