You are not logged in.
Openly accessible

Regret bounds for transfer learning in Bayesian optimisation

Shilton, Alistair, Gupta, Sunil, Rana, Santu and Venkatesh, Svetha 2017, Regret bounds for transfer learning in Bayesian optimisation, in AISTATS 2017 : Machine Learning Research : Proceedings of the 20th Artificial Intelligence and Statistics International Conference, Journal of Machine Learning Research (JMLR), [Fort Lauderdale, Fla.], pp. 1-9.

Attached Files
Name Description MIMEType Size Downloads
shilton-regretbounds-2017.pdf Published version application/pdf 349.67KB 8

Title Regret bounds for transfer learning in Bayesian optimisation
Author(s) Shilton, AlistairORCID iD for Shilton, Alistair orcid.org/0000-0002-0849-3271
Gupta, SunilORCID iD for Gupta, Sunil orcid.org/0000-0002-3308-1930
Rana, SantuORCID iD for Rana, Santu orcid.org/0000-0003-2247-850X
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Conference name Artificial Intelligence and Statistics. International Conference (20th : 2017 : Fort Lauderdale, Florida)
Conference location Fort Lauderdale, Florida
Conference dates 20-22 Apr. 2017
Title of proceedings AISTATS 2017 : Machine Learning Research : Proceedings of the 20th Artificial Intelligence and Statistics International Conference
Editor(s) Singh, Aarti
Zhu, Jerry
Publication date 2017
Conference series Proceedings of machine learning research, v.54
Start page 1
End page 9
Total pages 9
Publisher Journal of Machine Learning Research (JMLR)
Place of publication [Fort Lauderdale, Fla.]
Summary This paper studies the regret bound of two transfer learning algorithms in Bayesian optimisation. The first algorithm models any difference between the source and target functions as a noise process. The second algorithm proposes a new way to model the difference between the source and target as a Gaussian process which is then used to adapt the source data. We show that in both cases the regret bounds are tighter than in the no transfer case. We also experimentally compare the performance of these algorithms relative to no transfer learning and demonstrate benefits of transfer learning.
Language eng
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 0 Not Applicable
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2017, The Authors
Free to Read? Yes
Use Rights Creative Commons Attribution licence
Persistent URL http://hdl.handle.net/10536/DRO/DU:30094575

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 84 Abstract Views, 10 File Downloads  -  Detailed Statistics
Created: Mon, 29 May 2017, 10:24:43 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.