<i>al3c</i>: high-performance software for parameter inference using Approximate Bayesian Computation

Stram, Alexander; Marjoram, Paul; Chen, Gary K.

doi:10.1093/bioinformatics/btv393

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…pyABC addresses the need for distributed, likelihood-free inference for computationally demanding models. While pyABC's less scalable STAT strategy is also implemented elsewhere (Jennings and Madigan, 2017;Stram et al, 2015;Ishida et al, 2015), the runtime optimized, more scalable DYN strategy is, to the authors' knowledge, not available in any other ABC-SMC package. pyABC is the only framework featuring adaptive population size selection (Klinger and Hasenauer, 2017).…”

Section: Resultsmentioning

confidence: 99%

pyABC: distributed, likelihood-free inference

2018

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

pyABC: distributed, likelihood-free inference

2018

View full text Add to dashboard Cite

show abstract

“…Our goal is to overcome the need for users to have knowledge of parallel programming, as is required for using ABC-sysbio, and also to make a software package available for scientists across domains. These objectives were partly addressed by parallelization of SMCABC using MPI/OpenMPI (Stram, Marjoram, and Chen 2015), and by making SMCABC available for the astronomical community (Jennings and Madigan 2017). Regardless of these advances, a recent ABC review article (Lintusaari et al 2016) highlights the depth and breadth of available ABC algorithms, which can be made efficient via parallelization using an HPC environment (Kulakova, Angelikopoulos, Hadjidoukas, Papadimitriou, and Koumoutsakos 2016;Chiachio, Beck, Chiachio, and Rus 2014).…”

Section: Introductionmentioning

confidence: 99%

ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation

Dutta¹,

Schoengens²,

Pacchiardi³

et al. 2021

J. Stat. Soft.

View full text Add to dashboard Cite

ABCpy is a highly modular scientific library for approximate Bayesian computation (ABC) written in Python. The main contribution of this paper is to document a software engineering effort that enables domain scientists to easily apply ABC to their research without being ABC experts; using ABCpy they can easily run large parallel simulations without much knowledge about parallelization. Further, ABCpy enables ABC experts to easily develop new inference schemes and evaluate them in a standardized environment and to extend the library with new algorithms. These benefits come mainly from the modularity of ABCpy. We give an overview of the design of ABCpy and provide a performance evaluation concentrating on parallelization. This points us towards the inherent imbalance in some of the ABC algorithms. We develop a dynamic scheduling MPI implementation to mitigate this issue and evaluate the various ABC algorithms according to their adaptability towards high-performance computing.

show abstract

“…Our goal is to overcome the need for users to have knowledge of parallel programming, as is required for using ABC-sysbio, and also to make a software package available for scientists across domains. These objectives were partly addressed by parallelization of ABC-SMC using MPI/OpenMPI [Stram et al, 2015], and by making ABC-SMC available for the astronomical community [Jennings and Madigan, 2016]. Regardless of these advances, a recent ABC review article [Lintusaari et al, 2016] highlights the depth and breadth of available ABC algorithms, which can be made efficient via parallelization using an HPC environment [Kulakova et al, 2016, Chiachio et al, 2014.…”

Section: Introductionmentioning

confidence: 99%

ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation

Dutta,

Schoengens,

Pacchiardi

et al. 2017

Preprint

View full text Add to dashboard Cite

ABCpy is a highly modular scientific library for Approximate Bayesian Computation (ABC) written in Python. The main contribution of this paper is to document a software engineering effort that enables domain scientists to easily apply ABC to their research without being ABC experts; using ABCpy they can easily run large parallel simulations without much knowledge about parallelization. Further, ABCpy enables ABC experts to easily develop new inference schemes and evaluate them in a standardized environment and to extend the library with new algorithms. These benefits come mainly from the modularity of ABCpy. We give an overview of the design of ABCpy and provide a performance evaluation concentrating on parallelization. This points us towards the inherent imbalance in some of the ABC algorithms. We develop a dynamic scheduling MPI implementation to mitigate this issue and evaluate the various ABC algorithms according to their adaptability towards high-performance computing.

show abstract

al3c: high-performance software for parameter inference using Approximate Bayesian Computation

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 4 publications

References 12 publications

pyABC: distributed, likelihood-free inference

pyABC: distributed, likelihood-free inference

ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation

ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation

Contact Info

Product

Resources

About