News&Events

BIDSA Seminar: "Informed sub-sampling MCMC: Approximate Bayesian inference for large datasets"
| ROOM: 3.E4.SR03

| 21/03/2019 h.12.30
BIDSA Seminar: "Informed sub-sampling MCMC: Approximate Bayesian inference for large datasets"
Speaker: Nial Friel, University of Dublin

"Informed sub-sampling MCMC: Approximate Bayesian inference for large datasets"


21 March 2019, 12:30PM

Bocconi University, Room 3.e4.sr03

via Roentgen 1, 3rd floor


ABSTRACT

This talk introduces a framework for speeding up Bayesian inference for large datasets. We design a Markov chain whose transition kernel uses an (unknown) fraction of (fixed size) of the available data that is randomly refreshed throughout the algorithm. Inspired by the Approximate Bayesian Computation (ABC) literature, the subsampling process is guided by the fidelity to the observed data, as measured by summary statistics. The resulting algorithm, Informed Sub-Sampling MCMC (ISS-MCMC), is a generic and flexible approach which, contrary to existing scalable methodologies, preserves the simplicity of the Metropolis-Hastings algorithm. Even though exactness is lost, i.e. the chain distribution approximates the posterior, we study and quantify theoretically this bias and show on a diverse set of examples that it yields excellent performances when the computational budget is limited. This is joint work with Florian Maire (Montreal) and Pierre Alquier (INSAE, Paris).

Reference:
Maire, F., Friel, N. & Alquier, P. Informed sub-sampling MCMC: Approximate Bayesian Inference for Large Datasets. Statistics and Computing (2018). https://doi.org/10.1007/s11222-018-9817-3


SPEAKER


Nial Friel is a professor of statistics in University College Dublin. He is also a co-Principal Investigator in the Insight Centre for Data Analytics, where he leads the Machine Learning and Statistics programme. His research interests are in Bayesian statistics; Statistical network analysis; Monte Carlo methods.
mathsci.ucd.ie/~nial