Conference item icon

Conference item

Testing and learning on distributions with symmetric noise invariance

Abstract:

Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting distance between distributions, are useful tools for fully nonparametric two-sample testing and learning on distributions. However, it is rarely that all possible differences between samples are of interest – discovered differences can be due to different types of measurement noise, data collection artefacts or other irrelevant sources of variability. We propose distances between distributions which encod...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:

Authors


More by this author
Department:
Oxford, MPLS, Statistics
Role:
Author
More by this author
Department:
Oxford, MPLS, Statistics
Role:
Author
Publisher:
Curran Associates Publisher's website
Volume:
30
Pages:
1344-1354
Publication date:
2018-06-01
Acceptance date:
2017-09-04
ISSN:
1049-5258
Pubs id:
pubs:725615
URN:
uri:ed0c1a10-0c84-427c-9986-b97d9b599108
UUID:
uuid:ed0c1a10-0c84-427c-9986-b97d9b599108
Local pid:
pubs:725615
ISBN:
978-1-5108-6096-4

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP