Convergence, Robustness and Flexibility of Gaussian Process Regression

Add to your list(s) Download to your calendar using vCal

• Aretha Teckentrup (University of Edinburgh)
• Tuesday 08 June 2021, 15:00-16:00
• https://bham-ac-uk.zoom.us/j/3900445385?pwd=Mk1LSmRiUk5STEJMWVl0bE82NTM1QT09.

If you have a question about this talk, please contact Hong Duong.

We are interested in the task of estimating an unknown function from a set of point evaluations. In this context, Gaussian process regression is often used as a Bayesian inference procedure. However, hyper-parameters appearing in the mean and covariance structure of the Gaussian process prior, such as smoothness of the function and typical length scales, are often unknown and learnt from the data, along with the posterior mean and covariance.

In the first part of the talk, we will study the robustness of Gaussian process regression with respect to mis-specification of the hyper-parameters, and provide a convergence analysis of the method applied to a fixed, unknown function of interest [1].

In the second part of the talk, we discuss deep Gaussian processes as a class of flexible non-stationary prior distributions [2].

[1] A.L. Teckentrup. Convergence of Gaussian process regression with estimated hyper-parameters and applications in Bayesian inverse problems. SIAM /ASA Journal on Uncertainty Quantification, 8(4), p. 1310-1337, 2020.

[2] M.M. Dunlop, M.A. Girolami, A.M. Stuart, A.L. Teckentrup. How deep are deep Gaussian processes? Journal of Machine Learning Research, 19(54), 1-46, 2018.

This talk is part of the Data Science and Computational Statistics Seminar series.

This talk is included in these lists:

• Data Science and Computational Statistics Seminar
• School of Mathematics events
• https://bham-ac-uk.zoom.us/j/3900445385?pwd=Mk1LSmRiUk5STEJMWVl0bE82NTM1QT09

Note that ex-directory lists are not shown.