Chen, WY;
Mackey, L;
Gorham, J;
Briol, FX;
Oates, CJ;
(2018)
Stein points.
In: Dy, J and Krause, A, (eds.)
Proceedings of the 35th International Conference on Machine Learning.
(pp. pp. 844-853).
PMLR
Preview |
Text
Briol_Stein points_AAM.pdf - Accepted Version Download (7MB) | Preview |
Abstract
An important task in computational statistics and machine learning is to approximate a posterior distribution p(x) with an empirical measure supported on a set of representative points {x_{i}}_{i=1}^{n}. This paper focuses on methods where the selection of points is essentially deterministic, with an emphasis on achieving accurate approximation when n is small. To this end, we present Stein Points. The idea is to exploit either a greedy or a conditional gradient method to iteratively minimise a kernel Stein discrepancy between the empirical measure and p(x). Our empirical results demonstrate that Stein Points enable accurate approximation of the posterior at modest computational cost. In addition, theoretical results are provided to establish convergence of the method.
Type: | Proceedings paper |
---|---|
Title: | Stein points |
Event: | The 35th International Conference on Machine Learning |
Dates: | 10th-15th July 2018 |
ISBN-13: | 9781510867963 |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | http://proceedings.mlr.press/v80/chen18f.html |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/10079214 |
Archive Staff Only
View Item |