Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE

Dilin Wang; Qiang Liu

Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE

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 1707.00797 v1 pith:GNPOMZUK submitted 2017-07-04 stat.ML cs.LG

Qiang Liu , Dilin Wang This is my paper · ORCID

classification stat.MLcs.LG

keywords learningmodelsdeepenergyperformswellalgorithmsamortized

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generating realistic looking images. Our results suggest promising directions for learning better models by combining GAN-style methods with traditional energy-based learning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

Score Matching With Missing Data
stat.ML 2025-05 conditional novelty 6.0 of 10

The paper proposes two score matching objectives for partially missing data, proves a finite-sample bound for the truncated importance-weighted variant, and shows improved graphical model edge recovery on stock and ye...

Pith tools