STOR-i Seminar: Professor Chris Oates, Newcastle University

Friday 7 February 2025, 12:00pm to 1:00pm

Venue

PSC - PSC A54 - View Map

Open to

Postgraduates, Staff

Registration

Free to attend - registration required

Registration Info

This event is primarily for STOR-i students and staff.

Event Details

Prediction-Centric Uncertainty Quantification

Deterministic mathematical models, such as those specified via differential equations, are a powerful tool to communicate scientific insight. However, such models are necessarily simplified descriptions of the real world. Generalised Bayesian methodologies have been proposed for inference with misspecified models, but these are typically associated with vanishing parameter uncertainty as more data are observed. In the context of a misspecified deterministic mathematical model, this has the undesirable consequence that posterior predictions become deterministic and certain, while being incorrect. Taking this observation as a starting point, we propose Prediction-Centric Uncertainty Quantification, where a mixture distribution based on the deterministic model confers improved uncertainty quantification in the predictive context. (This is joint work with Zheyang Shen, Jeremias Knoblauch and Sam Power, which will appear in AISTATS 2025.)

Contact Details

Name Nicky Sarjent
Email

n.sarjent@lancaster.ac.uk

Telephone number

+44 1524 594362

Directions to PSC - PSC A54

On the bottom floor of the PSC, the LT at the end.