Year: 2015
Type: preprint
Abstract: We present doubly stochastic gradient MCMC, a simple and generic method for (approximate) Bayesian inference of deep generative models (DGMs) in a collapsed continuous parameter space. At each MCMC sampling step, the algorithm randomly draws a mini-batch of data samples to estimate the gradient of log-posterior and further estimates the intractable expectation over hidden variables via a neural adaptive importance sampler, where the proposal distribution is parameterized by a deep neural network and learnt jointly. We demonstrate the effectiveness on learning various DGMs in a wide range of tasks, including density estimation, data generation and missing data imputation. Our method outperforms many state-of-the-art competitors.
Source: arXiv (Cornell University)
Authors: Du, Chao, Zhu, Jun, Zhang, Bo
Institution: Tsinghua University
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1531388653