Turing data science class: An introduction to probabilistic numerical methods

Speaker: Chris Oates (Group Leader, Programme on Data-Centric Engineering)

Date: 30 October 2017

Time: 10:00 – 11:30

Registration: online registration is compulsory

Should this class be live streamed, you will be able to view it on our YouTube page

This seminar will explore numerical methods for optimisation, integration, linear algebra and solution of differential equations, all from the perspective of a Bayesian statistician – no background in numerical analysis will be assumed. The aim is to provide a crash course in Probabilistic Numerics – an exciting new area of statistical research – and to explain its relevance to decision-making based on computational output. The discussion will focus on a number of prototypical examples, with the general theory presented in [1].

[1] Cockayne J, Oates CJ, Sullivan T, Girolami M. Bayesian Probabilistic Numerical Methods.

This is an introductory class (no advanced session planned)