Skip to main content

Joint Econometrics and Statistics Workshop

Bayesian Optimal Experimental Design

Adam Foster (Microsoft Research AI4Science))

Friday 08 March 2024 14:00 - 15:00

Many of our seminars and public events this year will continue as in person or as hybrid (online and in person) events. Please check our website listings and Twitter feed @STICERD_LSE for updates.

Unless otherwise specified, in-person seminars are open to the public. Please ensure you have informed the event contact as early as possible.

Those unable to join the seminars in-person are welcome to participate via zoom if the event is hybrid.


About this event

In order to use machine learning in a domain without pre-existing data, we must first gather data by conducting experiments. This presents an opportunity, because we can design experiments carefully to ensure we gather the most informative data. As we gather a little data, we can use this to guide the design of future experiments in an adaptive manner. Bayesian Optimal Experiment Design (BOED) is a mathematical framework that precisely defines the optimal experiment in a pipeline like this. Historically, though, BOED has been computationally too challenging to use in practice. In this talk, I discuss recent computational advances in the field that utilise variational inference, gradient-based optimisation and policy learning to overcome many of these computational bottlenecks. I will also touch on applications such as adaptive survey design and force-field learning in AI for science.

Econometrics and Statistics seminars are held on Fridays in term time at 12:00-13:00, ONLINE, unless specified otherwise.

Seminar organisers: Dr Tatiana Komarova and Dr Yunxiao Chen.

For further information please contact Lubala Chibwe: l.chibwe@lse.ac.uk.

Please use this link to subscribe or unsubscribe to the Econometrics and Statistics seminars mailing list (stats).