Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
arXiv:1810.02555
Abstract
Stochastic optimization techniques are standard in variational inference algorithms. These methods estimate gradients by approximating expectations with independent Monte Carlo samples. In this paper, we explore a technique that uses correlated, but more representative , samples to reduce estimator variance. Specifically, we show how to generate antithetic samples that match sample moments with the true moments of an underlying importance distribution. Combining a differentiable antithetic sampler with modern stochastic variational inference, we showcase the effectiveness of this approach for learning a deep generative model.
arXiv comment8 pages with 7 pages appendix; AISTATS 2019
References in corpus (9)
- Auto-Encoding Variational Bayes
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Categorical Reparameterization with Gumbel-Softmax
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Variational Inference with Normalizing Flows
- Gradient Estimation Using Stochastic Computation Graphs
- The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
- Improving Variational Auto-Encoders using Householder Flow
- Training Variational Autoencoders with Buffered Stochastic Variational Inference