Using adjoint to accelerate inference in linear systems
As part of this year's IDSAI Research Seminar Series, Richard Wilkinson, Professor of Statistics, Faculty of Science, University of Nottingham will be presenting on using adjoint to accelerate inference in linear systems.
|An Institute for Data Science and Artificial Intelligence seminar|
|Date||28 September 2022|
|Time||14:00 to 15:00|
|Place||Queens Building LT7.1|
Hybrid delivery, by zoom
Linear systems occur (e.g. Lx=f) throughout engineering and the sciences, notably as differential equations. In many cases the forcing function (f) for the system is unknown, and interest lies in using noisy observations of the system (y=Ax+e) to infer the forcing, as well as other unknown parameters.
Richard Wilkinson will discuss his recent work that uses adjoints of linear systems to infer forcing functions modelled as Gaussian processes (GP). By using a truncated basis expansion, it is possible to do conjugate Bayesian inference for the GP, in many cases, with substantially lower computation than would be required using alternative methods. Richard will demonstrate the approach using an advection-diffusion model that arises in his attempts to model the spread of air pollution in Kampala, Uganda.
To be delivered hybrid. To register, please click here. Registration closes: Wednesday, 28 September 2022 at 09:00 (BST).
Whilst we appreciate the flexibility that hybrid delivery brings, we would encourage you to come along in person where there will be tea and coffee afterwards.
Further details to follow. If you have any queries, please contact email@example.com.
Queens Building LT7.1