Pith. sign in

REVIEW 1 cited by

On the Asymptotics of Importance Weighted Variational Inference

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 2501.08477 v1 pith:XZEESIZ6 submitted 2025-01-14 math.ST stat.TH

classification math.STstat.TH
keywords importancecarlodataexpectationinferencelatentlikelihoodmonte
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

For complex latent variable models, the likelihood function is not available in closed form. In this context, a popular method to perform parameter estimation is Importance Weighted Variational Inference. It essentially maximizes the expectation of the logarithm of an importance sampling estimate of the likelihood with respect to both the latent variable model parameters and the importance distribution parameters, the expectation being itself with respect to the importance samples. Despite its great empirical success in machine learning, a theoretical analysis of the limit properties of the resulting estimates is still lacking. We fill this gap by establishing consistency when both the Monte Carlo and the observed data sample sizes go to infinity simultaneously. We also establish asymptotic normality and efficiency under additional conditions relating the rate of growth between the Monte Carlo and the observed data samples sizes. We distinguish several regimes related to the smoothness of the importance ratio.

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

  1. Predictively Oriented Posteriors

    stat.ME 2025-10 conditional novelty 6.0 of 10

    A new posterior family scores the posterior predictive directly, giving slower concentration but better predictive performance under model misspecification.

Pith tools