Adaptive Tolerance Selection for SMC ABC

Sequential Monte Carlo approaches to approximate Bayesian computation (SMC-ABC) offer an efficient means to estimate posterior distributions in likelihood-free scenarios. Tolerance sequencing in SMC-ABC is critical to the efficiency of the algorithm. Simola (2020) proposes a method for adaptively selecting a sequence of tolerances in a different approach to ABC (PMC-ABC). We reduce the computational cost of implementing this approach and implement it to SMC-ABC. We utilise examples to demonstrate the computational efficiency improvements achieved.

Abhishek Varghese

Queensland University of Technology

Abhishek is in his final year of Bachelor of Electrical Engineering/Economics degree at QUT. He has both deep and broad talents and interests in data science. He serves as a Research Assistant at QUT and has developed skills through proactive engagement in several research projects with the Australian Research Council Centre of Excellence in Mathematical and Statistical Frontiers (ACEMS). His highlight project has involved estimating and modelling disease spread in a banana plantation which has recently been accepted by PLOS Computational Biology (top two per cent of Modelling and Simulation category according to Scimago).

You may be interested in

Cameron Eggins

Cameron Eggins

Convex Projective Surfaces
James McCusker

James McCusker

Quarternions And Octonions
Matthew Hanna

Matthew Hanna

Optimisation and Theoretical Implications of Probability Inequalities
Benjamin Solomon

Benjamin Solomon

Super Box-Ball Systems
Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text.