We are thrilled to announce that we will organise our Inaugural MFC Wednesday on 15th October at Imperial College London.
The day will be filled with engaging sessions for students, including talks by David Dritschel (U. St Andrews) and Pierre Gruet (EDF).
Speaker: Pierre Gruet (EDF)
Fast Gaussian process inference by exact Matérn kernel decomposition
(joint with Nicolas Langrené and Xavier Warin)
To speed up Gaussian process inference, a number of fast kernel matrix-vector multiplication (MVM) approximation algorithms have been proposed over the years. In this paper, we establish an exact fast kernel MVM algorithm based on exact kernel decomposition into weighted empirical cumulative distribution functions, compatible with a class of kernels which includes multivariate Matérn kernels with half-integer smoothness parameter. This algorithm uses a divide-and-conquer approach, during which sorting outputs are stored in a data structure. We also propose a new algorithm to take into account some linear fixed effects predictor function. Our numerical experiments confirm that our algorithm is very effective for low-dimensional Gaussian process inference problems with hundreds of thousands of data points. An implementation of our algorithm is available at this https URL.
Event Schedule – 15th October
| Time | Event | Venue |
|---|---|---|
| 11:00 AM – 12:00 PM | Talk by David Dritschel (University of St Andrews) |
Chemistry Building, CHEM 667 |
| 12:00 PM – 1:00 PM | Lunch | Chemistry Building, CHEM C661 |
| 1:00 PM – 2:00 PM | Talk by Pierre Gruet (EDF) |
Chemistry Building, CHEM 667 |
| 2:00 PM – 2:30 PM | Refreshment Break | Chemistry Building, CHEM C661 |
| 2:30 PM – 4:30 PM | Communications Training with Justine Jones (Cohort 2 only) | Huxley 642 |
| 4:30 PM Onwards | Cohort Social | East Side Bar |
Note: The Communication Training session from 2:30 PM is compulsory for Cohort 2.