# Optimizing Threshold - Schedules for Approximate Bayesian Computation Sequential Monte Carlo Samplers: Applications to Molecular Systems

@article{Silk2012OptimizingT, title={Optimizing Threshold - Schedules for Approximate Bayesian Computation Sequential Monte Carlo Samplers: Applications to Molecular Systems}, author={Daniel Silk and Stefano Filippi and Michael P. H. Stumpf}, journal={arXiv: Computation}, year={2012} }

The likelihood-free sequential Approximate Bayesian Computation (ABC) algorithms, are increasingly popular inference tools for complex biological models. Such algorithms proceed by constructing a succession of probability distributions over the parameter space conditional upon the simulated data lying in an $\epsilon$--ball around the observed data, for decreasing values of the threshold $\epsilon$. While in theory, the distributions (starting from a suitably defined prior) will converge…

## 11 Citations

On optimality of kernels for approximate Bayesian computation using sequential Monte Carlo

- Computer ScienceStatistical applications in genetics and molecular biology
- 2013

This paper discusses how to construct the perturbation kernels that are required in ABC SMC approaches, in order to construct a sequence of distributions that start out from a suitably defined prior and converge towards the unknown posterior.

A framework for parameter estimation and model selection from experimental data in systems biology using approximate Bayesian computation

- Computer ScienceNature Protocols
- 2014

An approximate Bayesian computation framework and software environment, ABC-SysBio, which is a Python package that runs on Linux and Mac OS X systems and that enables parameter estimation and model selection in the Bayesian formalism by using sequential Monte Carlo (SMC) approaches is presented.

Sequential Monte Carlo with Adaptive Weights for Approximate Bayesian Computation

- Computer Science
- 2015

An ABC SMC method that uses data-based adaptive weights can very substantially improve acceptance rates, as is demonstrated in a series of examples with simulated and real data sets, including a currently topical example from dynamic modelling in systems biology applications.

Approximate Bayesian Computation for Forward Modeling in Cosmology

- Computer Science
- 2015

Approximate Bayesian Computation (ABC) is found to provide reliable parameter constraints for this problem and is therefore a promising technique for other applications in cosmology and astrophysics.

An Approximate Likelihood Perspective on ABC Methods

- Computer Science
- 2017

This article provides a unifying review, general representation, and classification of all ABC methods from the view of approximate likelihood theory, which clarifies how ABC methods can be characterized, related, combined, improved, and applied for future research.

Approximate Bayesian Computation and simulation based inference for complex stochastic epidemic models

- Computer Science
- 2018

This work uses a real-world model of HIV transmission to illustrate some of challenges when applying ABC methods to high-dimensional, computationally intensive models, and discusses an alternative approach that aims to address some of these issues.

Approximate Bayesian Computation Methods in the Identification of Atmospheric Contamination Sources for DAPPLE Experiment

- Environmental Science
- 2016

Sudden releases of harmful material into a densely-populated area pose a significant risk to human health. The apparent problem of determining the source of an emission in urban and industrialized…

ABC Samplers

- Computer ScienceHandbook of Approximate Bayesian Computation
- 2018

This Chapter details the main ideas and algorithms used to sample from the ABC approximation to the posterior distribution, including methods based on rejection/importance sampling, MCMC and sequential Monte Carlo.

Fisher information distance: a geometrical reading?

- Computer Science, MathematicsDiscret. Appl. Math.
- 2015

Approximate Bayesian computation for complex dynamic systems

- Computer Science
- 2013

Approximate Bayesian Computation for Complex Dynamic Systems shows good agreement between the values obtained in the discrete-time model and the values observed in the real world.

## References

SHOWING 1-10 OF 31 REFERENCES

An adaptive sequential Monte Carlo method for approximate Bayesian computation

- Computer Science, MathematicsStat. Comput.
- 2012

An adaptive SMC algorithm is proposed which admits a computational complexity that is linear in the number of samples and adaptively determines the simulation parameters.

On optimality of kernels for approximate Bayesian computation using sequential Monte Carlo

- Computer ScienceStatistical applications in genetics and molecular biology
- 2013

This paper discusses how to construct the perturbation kernels that are required in ABC SMC approaches, in order to construct a sequence of distributions that start out from a suitably defined prior and converge towards the unknown posterior.

On Optimal Selection of Summary Statistics for Approximate Bayesian Computation

- Computer ScienceStatistical applications in genetics and molecular biology
- 2010

It was found that the optimal set of summary statistics was highly dataset specific, suggesting that more generally there may be no globally-optimal choice, which argues for a new selection for each dataset even if the model and target of inference are unchanged.

Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems

- Computer Science, MathematicsJournal of The Royal Society Interface
- 2008

This paper discusses and applies an ABC method based on sequential Monte Carlo (SMC) to estimate parameters of dynamical models and develops ABC SMC as a tool for model selection; given a range of different mathematical descriptions, it is able to choose the best model using the standard Bayesian model selection apparatus.

Adaptive approximate Bayesian computation for complex models

- Computer ScienceComput. Stat.
- 2013

A new approximate Bayesian computation (ABC) algorithm that aims at minimizing the number of model runs for reaching a given quality of the posterior approximation and makes use of an easily interpretable stopping criterion.

Estimation of Parameters for Macroparasite Population Evolution Using Approximate Bayesian Computation

- Computer ScienceBiometrics
- 2011

The ABC algorithm presented is based on sequential Monte Carlo, is adaptive in nature, and overcomes some drawbacks of previous approaches to ABC.

Comparative Evaluation of a New Effective Population Size Estimator Based on Approximate Bayesian Computation

- MathematicsGenetics
- 2004

Simulations of a Wright-Fisher population with known Ne show that theSummStat estimator is useful across a realistic range of individuals and loci sampled, generations between samples, and Ne values, and under the conditions simulated, SummStat confidence intervals were more conservative than the likelihood-based estimators and more likely to include true Ne.

Non-linear regression models for Approximate Bayesian Computation

- Computer ScienceStat. Comput.
- 2010

A machine-learning approach to the estimation of the posterior density by introducing two innovations that fits a nonlinear conditional heteroscedastic regression of the parameter on the summary statistics, and then adaptively improves estimation using importance sampling.

Markov chain Monte Carlo without likelihoods

- MathematicsProceedings of the National Academy of Sciences of the United States of America
- 2003

A Markov chain Monte Carlo method for generating observations from a posterior distribution without the use of likelihoods is presented, which can be used in frequentist applications, in particular for maximum-likelihood estimation.

Approximately Sufficient Statistics and Bayesian Computation

- MathematicsStatistical applications in genetics and molecular biology
- 2008

A sequential scheme for scoring statistics according to whether their inclusion in the analysis will substantially improve the quality of inference, which can be applied to high-dimensional data sets for which exact likelihood equations are not possible.