Approximate Inference with Amortised MCMC

1 149
38.3
Следующее
Популярные
08.11.23 – 1 3681:52
Project Mosaic
Опубликовано 19 мая 2017, 22:50
We propose a novel approximate inference algorithm that approximates a target distribution by amortising the dynamics of a user-selected MCMC sampler. The idea is to initialise MCMC using samples from an approximation network, apply the MCMC operator to improve these samples, and finally use the samples to update the approximation network thereby improving its quality. This provides a new generic framework for approximate inference, allowing us to deploy highly complex, or implicitly defined approximation families with intractable densities, including approximations produced by warping a source of randomness through a deep neural network. Experiments consider image modelling with deep generative models as a challenging test for the method. Deep models trained using amortised MCMC are shown to generate realistic looking samples as well as producing diverse imputations for images with regions of missing pixels.

See more on this video at microsoft.com/en-us/research/v...
Свежие видео
6 дней – 2 3510:54
Angular v19 is here!
11 дней – 13 7282:25
AI Summit India 2024 Highlights
11 дней – 3 34438:03
Ultra HDR images | Android Build Time
Случайные видео
38 дней – 57 2021:15
Xiaomi Renovation 2024 Teaser
26.10.19 – 7 4242:58
Speeding up TensorFlow with TPUs
автотехномузыкадетское