Pith. sign in

REVIEW 1 cited by

Bounding the Test Log-Likelihood of Generative Models

Not yet reviewed by Pith; the record is open.

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 1311.6184 v4 pith:2ULY4EYY submitted 2013-11-24 cs.LG

classification cs.LG
keywords estimatormodelprobabilitysamplesfunctiongeneratedgenerativelog-likelihood
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Several interesting generative learning algorithms involve a complex probability distribution over many random variables, involving intractable normalization constants or latent variable normalization. Some of them may even not have an analytic expression for the unnormalized probability function and no tractable approximation. This makes it difficult to estimate the quality of these models, once they have been trained, or to monitor their quality (e.g. for early stopping) while training. A previously proposed method is based on constructing a non-parametric density estimator of the model's probability function from samples generated by the model. We revisit this idea, propose a more efficient estimator, and prove that it provides a lower bound on the true test log-likelihood, and an unbiased estimator as the number of generated samples goes to infinity, although one that incorporates the effect of poor mixing. We further propose a biased variant of the estimator that can be used reliably with a finite number of samples for the purpose of model comparison.

Discussion (0). Sign in 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

  1. Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

    cs.LG 2025-05 conditional novelty 6.0 of 10

    The diffusion Fisher matrix of a Gaussian-perturbed distribution is expressed in the span of data outer products, enabling two faster approximation algorithms for trace and matrix-vector access.

Pith tools