Pith. sign in

REVIEW 2 cited by

Stein Neural 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 1810.03545 v2 pith:2HWQNF5G submitted 2018-10-08 stat.ML cs.LG

Tianyang Hu , Zixiang Chen , Hanxi Sun , Jincheng Bai , Mao Ye , Guang Cheng This is my paper · ORCID
classification stat.MLcs.LG
keywords samplersdistributiongeneratenetworksneuralsamplessteinun-normalized
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose two novel samplers to generate high-quality samples from a given (un-normalized) probability density. Motivated by the success of generative adversarial networks, we construct our samplers using deep neural networks that transform a reference distribution to the target distribution. Training schemes are developed to minimize two variations of the Stein discrepancy, which is designed to work with un-normalized densities. Once trained, our samplers are able to generate samples instantaneously. We show that the proposed methods are theoretically sound and experience fewer convergence issues compared with traditional sampling approaches according to our empirical studies.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. On the Statistical Capacity of Deep Generative Models

    stat.ML 2025-01 conditional novelty 6.0 of 10

    Push-forwards of Gaussian or log-concave latent variables through Lipschitz neural networks are always sub-Gaussian or sub-exponential, so common deep generative models cannot generate heavy-tailed distributions.

  2. Path-Guided Particle-based Sampling

    cs.LG 2024-12 conditional novelty 5.0 of 10

    PGPS trains a neural velocity field to transport particles along a log-weighted shrinkage density path, giving a Wasserstein error bound of O(delta) + O(sqrt(h)) and improved mode seeking in Bayesian inference.

Pith tools