Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms
arXiv:1610.05683
Abstract
Variational inference using the reparameterization trick has enabled large-scale approximate Bayesian inference in complex probabilistic models, leveraging stochastic optimization to sidestep intractable expectations. The reparameterization trick is applicable when we can simulate a random variable by applying a differentiable deterministic function on an auxiliary random variable whose distribution is fixed. For many distributions of interest (such as the gamma or Dirichlet), simulation of random variables relies on acceptance-rejection sampling. The discontinuity introduced by the accept-reject step means that standard reparameterization tricks are not applicable. We propose a new method that lets us leverage reparameterization gradients even when variables are outputs of a acceptance-rejection sampling algorithm. Our approach enables reparameterization on a larger class of variational distributions. In several studies of real and synthetic data, we show that the variance of the estimator of the gradient is significantly lower than other state-of-the-art methods. This leads to faster convergence of stochastic gradient variational inference.
arXiv commentAn error in the von Mises distribution reparameterization in Table 2 has been corrected
References in corpus (10)
- Auto-Encoding Variational Bayes
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Auxiliary Deep Generative Models
- Automatic Differentiation Variational Inference
- Neural Variational Inference and Learning in Belief Networks
- Gradient Estimation Using Stochastic Computation Graphs
- Variational Bayesian Inference with Stochastic Search
- Stochastic gradient variational Bayes for gamma approximating distributions
- Fast Second-Order Stochastic Backpropagation for Variational Inference