A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI
arXiv:1706.06529
Abstract
Two popular classes of methods for approximate inference are Markov chain Monte Carlo (MCMC) and variational inference. MCMC tends to be accurate if run for a long enough time, while variational inference tends to give better approximations at shorter time horizons. However, the amount of time needed for MCMC to exceed the performance of variational methods can be quite high, motivating more fine-grained tradeoffs. This paper derives a distribution over variational parameters, designed to minimize a bound on the divergence between the resulting marginal distribution and the target, and gives an example of how to sample from this distribution in a way that interpolates between the behavior of existing methods based on Langevin dynamics and stochastic gradient variational inference (SGVI).
arXiv commentInternational Conference on Machine Learning (ICML) 2017
References in corpus (8)
- Variational Inference with Normalizing Flows
- Variational Dropout and the Local Reparameterization Trick
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
- Variational Bayesian Inference with Stochastic Search
- Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring
- On Using Control Variates with Stochastic Approximation for Variational Bayes and its Connection to Stochastic Linear Regression
- Smoothed Gradients for Stochastic Variational Inference