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
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.
Forward citations
Cited by 2 Pith papers
-
Indirect Variational Inference: Applications to Earnings Dynamics
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.
-
AVATAR: Adversarial Autoencoders with Autoregressive Refinement for Time Series Generation
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.
Discussion (0). Continue with ORCID to comment.