Delayed acceptance ABC-SMC

Everitt, Richard G.; Rowińska, Paulina A.

doi:10.48550/arxiv.1708.02230

Cited by 3 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Delayed-acceptance has been used to speed up a number of costly MCMC algorithms including pseudo-marginal methods (Golightly et al 2015, Wiqvist et al 2018, approximate Bayesian computing (ABC, Everitt & Rowińska 2017), and Bayesian inverse problems (Cui et al 2011). It has also been combined with data subsampling (Quiroz et al 2018) and consensus MCMC (Payne & Mallick 2018) to produce more general algorithms for accelerated MCMC.…”

Section: Delayed-acceptance Metropolis-hastingsmentioning

confidence: 99%

“…Such a partition has also been used for ABC. In particular, early rejection based on the prior can avoid the expensive simulation required to evaluate the indicator kernel (Everitt & Rowińska 2017). Lazy ABC (Prangle 2016) is another example of work in speeding up Bayesian computation.…”

Section: Delayed-acceptance Metropolis-hastingsmentioning

confidence: 99%

“…As mentioned, delayed-acceptance has been used in sequential Monte Carlo previously by Everitt & Rowińska (2017) for ABC where the surrogate model is a cheap, but approximate simulator. The novel adaptation strategy we describe can also be used in ABC-SMC, but is not limited to this type of Bayesian inference.…”

Section: Delayed-acceptance Metropolis-hastingsmentioning

confidence: 99%

“…The aim of this paper is to develop novel delayed-acceptance methods that are efficient and automated by harnessing the SMC framework. DA has been leveraged in SMC previously in the setting of approximate Bayesian computing (Everitt & Rowińska 2017). We propose surrogate accelerated SMC to improve delayed-acceptance, and use of surrogate likelihoods in SMC, through three avenues, which also constitute the main contributions of this work.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Accelerating sequential Monte Carlo with surrogate likelihoods

Bon¹,

Lee²,

Drovandi³

2020

Preprint

View full text Add to dashboard Cite

Delayed-acceptance is a technique for reducing computational effort for Bayesian models with expensive likelihoods. Using a delayed-acceptance kernel for Markov chain Monte Carlo can reduce the number of expensive likelihoods evaluations required to approximate a posterior expectation. Delayed-acceptance uses a surrogate, or approximate, likelihood to avoid evaluation of the expensive likelihood when possible. Within the sequential Monte Carlo framework, we utilise the history of the sampler to adaptively tune the surrogate likelihood to yield better approximations of the expensive likelihood, and use a surrogate first annealing schedule to further increase computational efficiency. Moreover, we propose a framework for optimising computation time whilst avoiding particle degeneracy, which encapsulates existing strategies in the literature. Overall, we develop a novel algorithm for computationally efficient SMC with expensive likelihood functions. The method is applied to static Bayesian models, which we demonstrate on toy and real examples, code for which is available at https://github.com/bonStats/smcdar.

show abstract

Section: Delayed-acceptance Metropolis-hastingsmentioning

confidence: 99%

Section: Delayed-acceptance Metropolis-hastingsmentioning

confidence: 99%

Section: Delayed-acceptance Metropolis-hastingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accelerating sequential Monte Carlo with surrogate likelihoods

Bon¹,

Lee²,

Drovandi³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Some implementations of the DA approach in Bayesian inference can be found e.g. in , , and Banterle et al [2015], and similar approaches based on approximate Bayesian computation (ABC) can be found in Picchini [2014], Picchini and Forman [2016], and Everitt and Rowi ńska [2017].…”

Section: Introductionmentioning

confidence: 99%

Accelerating delayed-acceptance Markov chain Monte Carlo algorithms

Wiqvist,

Picchini,

Forman

et al. 2018

Preprint

View full text Add to dashboard Cite

Delayed-acceptance Markov chain Monte Carlo (DA-MCMC) samples from a probability distribution via a two-stages version of the Metropolis-Hastings algorithm, by combining the target distribution with a "surrogate" (i.e. an approximate and computationally cheaper version) of said distribution. DA-MCMC accelerates MCMC sampling in complex applications, while still targeting the exact distribution. We design a computationally faster, albeit approximate, DA-MCMC algorithm. We consider parameter inference in a Bayesian setting where a surrogate likelihood function is introduced in the delayed-acceptance scheme. When the evaluation of the likelihood function is computationally intensive, our scheme produces a 2-4 times speed-up, compared to standard DA-MCMC. However, the acceleration is highly problem dependent. Inference results for the standard delayed-acceptance algorithm and our approximated version are similar, indicating that our algorithm can return reliable Bayesian inference. As a computationally intensive case study, we introduce a novel stochastic differential equation model for protein folding data.

show abstract

Rapid Bayesian inference for expensive stochastic models

Warne¹,

Baker²,

Simpson³

2019

Preprint

View full text Add to dashboard Cite

Almost all fields of science rely upon statistical inference to estimate unknown parameters in theoretical and computational models. While the performance of modern computer hardware continues to grow, the computational requirements for the simulation of models are growing even faster. This is largely due to the increase in model complexity, often including stochastic dynamics, that is necessary to describe and characterize phenomena observed using modern, high resolution, experimental techniques. Such models are rarely analytically tractable, meaning that extremely large numbers of expensive stochastic simulations are required for parameter inference. In such cases, parameter inference can be practically impossible. In this work, we present new computational Bayesian techniques that accelerate inference for expensive stochastic models by using computationally cheap approximations to inform feasible regions in parameter space, and through learning transforms that adjust the biased approximate inferences to closer represent the correct inferences under the expensive stochastic model. Using topical examples from ecology and cell biology, we demonstrate a speed improvement of an order of magnitude without any loss in accuracy.

show abstract

Delayed acceptance ABC-SMC

Cited by 3 publications

References 24 publications

Accelerating sequential Monte Carlo with surrogate likelihoods

Accelerating sequential Monte Carlo with surrogate likelihoods

Accelerating delayed-acceptance Markov chain Monte Carlo algorithms

Rapid Bayesian inference for expensive stochastic models

Contact Info

Product

Resources

About