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.
On the Quantitative Analysis of Decoder-Based Generative Models
1 Pith paper cite this work. Polarity classification is still indexing.
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.
citation-role summary
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
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.