← Back to OpenAI updates ← Terug naar OpenAI-updates
OpenAI ARTICLE ARTIKEL 14 November 2016 14 november 2016

On the quantitative analysis of decoder-based generative models On the quantitative analysis of decoder-based generative models

Read paper(opens in a new window) Read paper(opens in a new window)

Article details Artikelgegevens
AI maker AI-maker OpenAI Type Type Article Artikel Published Gepubliceerd 14 November 2016 14 november 2016 Updates Updates Videos Video's View original article Bekijk origineel artikel

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 atthis https URL⁠(opens in a new window). 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.

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 atthis https URL⁠(opens in a new window). 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.

Authors

Yuhuai Wu, Yura Burda, Ruslan Salakhutdinov, Roger Grosse

Related articles

View all

Hierarchical text-conditional image generation with CLIP latents Publication Apr 13, 2022

DALL·E: Creating images from text Milestone Jan 5, 2021

Image GPT Publication Jun 17, 2020

Image GPT Publication Jun 17, 2020

More from OpenAI Meer van OpenAI

All updates Alle updates

Gemini komt eraan