Imperial College London
Portrait Picture

ProfessorDavidSharp

Faculty of Medicine, Department of Brain Sciences

Professor of Neurology
 
 
 
//

Contact

 

+44 (0)20 7594 7991david.sharp Website

 
 
//

Location

 

UREN.927Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Popescu:2020,
author = {Popescu, S and Sharp, D and Cole, J and Glocker, B},
publisher = {arXiv},
title = {Hierarchical Gaussian processes with Wasserstein-2 kernels},
url = {http://arxiv.org/abs/2010.14877v1},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - We investigate the usefulness of Wasserstein-2 kernels in the context ofhierarchical Gaussian Processes. Stemming from an observation that stackingGaussian Processes severely diminishes the model's ability to detect outliers,which when combined with non-zero mean functions, further extrapolates lowvariance to regions with low training data density, we posit that directlytaking into account the variance in the computation of Wasserstein-2 kernels isof key importance towards maintaining outlier status as we progress through thehierarchy. We propose two new models operating in Wasserstein space which canbe seen as equivalents to Deep Kernel Learning and Deep GPs. Through extensiveexperiments, we show improved performance on large scale datasets and improvedout-of-distribution detection on both toy and real data.
AU  - Popescu,S
AU  - Sharp,D
AU  - Cole,J
AU  - Glocker,B
PB  - arXiv
PY  - 2020///
TI  - Hierarchical Gaussian processes with Wasserstein-2 kernels
UR  - http://arxiv.org/abs/2010.14877v1
UR  - http://hdl.handle.net/10044/1/88942
ER  -
Download