Pith. sign in

REVIEW 2 cited by

On the Quantitative Analysis of Decoder-Based 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 1611.04273 v2 pith:676DMMQM submitted 2016-11-14 cs.LG

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

The past several years have seen remarkable progress in generative models which produce convincing samples of images and other modalities. A shared component of many powerful generative models is a decoder network, a parametric deep neural net that defines a generative distribution. Examples include variational autoencoders, generative adversarial networks, and generative moment matching networks. Unfortunately, it can be difficult to quantify the performance of these models because of the intractability of log-likelihood estimation, and inspecting samples can be misleading. We propose to use Annealed Importance Sampling for evaluating log-likelihoods for decoder-based models and validate its accuracy using bidirectional Monte Carlo. The evaluation code is provided at https://github.com/tonywu95/eval_gen. Using this technique, we analyze the performance of decoder-based models, the effectiveness of existing log-likelihood estimators, the degree of overfitting, and the degree to which these models miss important modes of the data distribution.

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. Indirect Variational Inference: Applications to Earnings Dynamics

    econ.GN 2026-07 conditional novelty 7.0 of 10

    Indirect variational inference treats a variational approximation as an auxiliary model and inverts its binding function, correcting the bias of variational estimates in nonlinear earnings dynamics.

  2. AVATAR: Adversarial Autoencoders with Autoregressive Refinement for Time Series Generation

    cs.LG 2025-01 conditional novelty 4.0 of 10

    AVATAR augments adversarial autoencoders with an autoregressive supervisor and a mean-std distribution loss, reporting improved time series generation over five baselines on three datasets.

Pith tools