Journal article icon

Journal article

Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU

Abstract:

Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms. The focus is on machine learning, and as such includes features such as CPU parallelism, GPU support, and backpropagation. To our knowledge it is the first GPU-capable library for these operations. Signatory implements new features not available in previous libraries, such as efficient precomputation strategies. Furthermore, several novel algorithmic improvements are intro...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publication website:
https://openreview.net/forum?id=lqU2cs3Zca

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Oxford college:
St Hilda's College
Role:
Author
Article number:
Poster 2220
Publication date:
2021-05-03
Acceptance date:
2021-01-07
Event title:
International Conference on Learning Representations 2021
Event location:
Online
Event website:
https://openreview.net/group?id=ICLR.cc/2021/Conference
Event start date:
2021-05-03T00:00:00Z
Event end date:
2021-05-07T00:00:00Z
Language:
English
Keywords:
Pubs id:
1082290
Local pid:
pubs:1082290
Deposit date:
2021-02-18

Terms of use


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