Speeding Up MCMC by Delayed Acceptance and Data Subsampling
arXiv:1507.06110 · doi:10.1080/10618600.2017.1307117
Abstract
The complexity of the Metropolis-Hastings (MH) algorithm arises from the requirement of a likelihood evaluation for the full data set in each iteration. Payne and Mallick (2015) propose to speed up the algorithm by a delayed acceptance approach where the acceptance decision proceeds in two stages. In the first stage, an estimate of the likelihood based on a random subsample determines if it is likely that the draw will be accepted and, if so, the second stage uses the full data likelihood to decide upon final acceptance. Evaluating the full data likelihood is thus avoided for draws that are unlikely to be accepted. We propose a more precise likelihood estimator which incorporates auxiliary information about the full data likelihood while only operating on a sparse set of the data. We prove that the resulting delayed acceptance MH is more efficient compared to that of Payne and Mallick (2015). The caveat of this approach is that the full data set needs to be evaluated in the second stage. We therefore propose to substitute this evaluation by an estimate and construct a state-dependent approximation thereof to use in the first stage. This results in an algorithm that (i) can use a smaller subsample m by leveraging on recent advances in Pseudo-Marginal MH (PMMH) and (ii) is provably within of the true posterior.
arXiv commentAccepted for publication in Journal of Computational and Graphical Statistics
References in corpus (14)
- The pseudo-marginal approach for efficient Monte Carlo computations
- 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 Markov chain Monte Carlo methods for tall data
- On Russian Roulette Estimates for Bayesian Inference with Doubly-Intractable Likelihoods
- Parallelizing MCMC via Weierstrass Sampler
- The Penalty Method for Random Walks with Uncertain Energies
- Delayed acceptance particle MCMC for exact inference in stochastic kinetic models
- Firefly Monte Carlo: Exact MCMC with Subsets of Data
- On nonnegative unbiased estimators
- Coupled MCMC with a randomized acceptance probability
- Accelerating Metropolis-Hastings algorithms: Delayed acceptance with prefetching
- Light and Widely Applicable MCMC: Approximate Bayesian Inference for Large Datasets
Cited by in corpus (15)
- Speeding Up MCMC by Efficient Data Subsampling
- Approximating Bayes in the 21st Century
- Hamiltonian Monte Carlo with Energy Conserving Subsampling
- The Block Pseudo-Marginal Sampler
- Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance
- Computing Bayes: From Then 'Til Now'
- A survey of Monte Carlo methods for noisy and costly densities with application to reinforcement learning and ABC
- Accelerating delayed-acceptance Markov chain Monte Carlo algorithms
- Spectral Subsampling MCMC for Stationary Time Series
- The block-Poisson estimator for optimally tuned exact subsampling MCMC
- Flexible Bayesian Nonlinear Model Configuration
- Deep Bayesian regression models
- Accelerating sequential Monte Carlo with surrogate likelihoods
- Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets
- Subsampling MCMC - An introduction for the survey statistician