Machine Learning Coffee seminar "Efficient and accurate approximate Bayesian computation"

Event type: 
HIIT seminar
Event time: 
06.11.2017 - 09:15 - 10:00
Lecturer : 
Pekka Marttinen
Konemiehentie 2, seminar room T5

Pekka Marttinen, Academy Research Fellow, Department of Computer Science, Aalto University

Efficient and accurate approximate Bayesian computation

Abstract: Approximate Bayesian computation (ABC) is a method for calculating a posterior distribution when the likelihood is intractable, but simulating the model is feasible. It has numerous important applications, for example in computational biology, material physics, user interface design, etc. However, many ABC algorithms require a large number of simulations, which can be costly. To reduce the cost, Bayesian optimisation (BO) and surrogate models such as Gaussian processes have been proposed. Bayesian optimisation enables deciding intelligently where to simulate the model next, but standard BO approaches are designed for optimisation and not for ABC. Here we address this gap in the existing methods. We model the uncertainty in the ABC posterior density which is due to a limited number of simulations available, and define a loss function that measures this uncertainty. We then propose to select the next model simulation to minimise the expected loss. Experiments show the proposed method is often more accurate than the existing alternatives.

Machine Learning Coffee seminars are weekly seminars held jointly by the Aalto University and the University of Helsinki. The seminars aim to gather people from different fields of science with interest in machine learning. Talks will begin at 9:15 am and porridge and coffee will be served from 9:00 am.

Next talks:

Nov 13, Kumpula: Jukka Corander "Learning of Ultra High-Dimensional Potts Models for Bacterial Population Genomics"

Nov 20, Otaniemi: Perttu Hämäläinen "Towards Intelligent Exergames"

Nov 27, Kumpula: Erik Aurell


26.10.2017 - 11:33 Teemu Roos
26.10.2017 - 11:33 Teemu Roos