Conference item
GLASSES: Relieving the myopia of Bayesian optimisation
- Abstract:
-
We present glasses: Global optimisation with Look-Ahead through Stochastic Simulation and Expected-loss Search. The majority of global optimisation approaches in use are myopic, in only considering the impact of the next function value; the non-myopic approaches that do exist are able to consider only a handful of future evaluations. Our novel algorithm, glasses, permits the consideration of dozens of evaluations into the future. This is done by approximating the ideal look-ahead loss functio...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Journal of Machine Learning Research Publisher's website
- Host title:
- JMLR: Workshop and Conference Proceedings: Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS)
- Journal:
- JMLR: Workshop and Conference Proceedings Journal website
- Volume:
- 41
- Pages:
- 790–799
- Publication date:
- 2016-01-01
- Acceptance date:
- 2015-10-09
- Event location:
- Cadiz
- Event start date:
- 2016-05-09
- Event end date:
- 2016-05-11
- ISSN:
-
1938-7228
Item Description
- Pubs id:
-
pubs:664825
- UUID:
-
uuid:40919a8e-fcd4-4ee2-80cf-9a9b77df23c5
- Local pid:
- pubs:664825
- Source identifiers:
-
664825
- Deposit date:
- 2016-12-09
Terms of use
- Copyright holder:
- González et al
- Copyright date:
- 2016
- Notes:
-
Copyright
2016 by the authors.
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record