Hamiltonian Monte Carlo with Energy Conserving Subsampling

Abstract

Hamiltonian Monte Carlo (HMC) samples efficiently from high-dimensional posterior distributions with proposed parameter draws obtained by iterating on a discretized version of the Hamiltonian dynamics. The iterations make HMC computationally costly, especially in problems with large datasets, since it is necessary to compute posterior densities and their derivatives with respect to the parameters. Naively computing the Hamiltonian dynamics on a subset of the data causes HMC to lose its key ability to generate distant parameter proposals with high acceptance probability. The key insight in our article is that efficient subsampling HMC for the parameters is possible if both the dynamics and the acceptance probability are computed from the same data subsample in each complete HMC iteration. We show that this is possible to do in a principled way in a HMC-within-Gibbs framework where the subsample is updated using a pseudo marginal MH step and the parameters are then updated using an HMC step, based on the current subsample. We show that our subsampling methods are fast and compare favorably to two popular sampling algorithms that utilize gradient estimates from data subsampling. We also explore the current limitations of subsampling HMC algorithms by varying the quality of the variance reducing control variates used in the estimators of the posterior density and its gradients.

Includes an experiment on the scalability of the method. Text has been revised too

References in corpus (17)

• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• General state space Markov chains and MCMC algorithms
• The pseudo-marginal approach for efficient Monte Carlo computations
• A Conceptual Introduction to Hamiltonian Monte Carlo
• Stochastic Gradient Hamiltonian Monte Carlo
• On the efficiency of pseudo-marginal random walk Metropolis algorithms
• Austerity in MCMC Land: Cutting the Metropolis-Hastings Budget
• Speeding Up MCMC by Efficient Data Subsampling
• On Russian Roulette Estimates for Bayesian Inference with Doubly-Intractable Likelihoods
• Parallelizing MCMC via Weierstrass Sampler
• Firefly Monte Carlo: Exact MCMC with Subsets of Data
• Speeding Up MCMC by Delayed Acceptance and Data Subsampling
• The promises and pitfalls of Stochastic Gradient Langevin Dynamics
• Coupled MCMC with a randomized acceptance probability
• Pseudo-Marginal Hamiltonian Monte Carlo
• Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling
• The Block Pseudo-Marginal Sampler

Cited by in corpus (4)

• Speeding Up MCMC by Efficient Data Subsampling
• Distributed Computation for Marginal Likelihood based Model Choice
• Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets
• Subsampling MCMC - An introduction for the survey statistician