Conference item
Online optimization of smoothed piecewise constant functions
- Abstract:
-
We study online optimization of smoothed piecewise constant functions over the domain [0, 1). This is motivated by the problem of adaptively picking parameters of learning algorithms as in the recently introduced framework by Gupta and Roughgarden (2016). Majority of the machine learning literature has focused on Lipschitz-continuous functions or functions with bounded gradients.1 This is with good reason—any learning algorithm suffers linear regret even against piecewise constant functions t...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Proceedings of Machine Learning Research Publisher's website
- Host title:
- Proceedings of the 20th International Conference on Artificial Intelligence and Statistics
- Series:
- Proceedings of Machine Learning Research
- Volume:
- 54
- Pages:
- 412-420
- Publication date:
- 2017-01-01
- Acceptance date:
- 2017-01-24
- ISSN:
-
1938-7228
Item Description
- Pubs id:
-
pubs:673197
- UUID:
-
uuid:8e50e930-b696-4fde-9597-6d471e7d5515
- Local pid:
- pubs:673197
- Source identifiers:
-
673197
- Deposit date:
- 2017-01-26
Terms of use
- Copyright holder:
- Cohen-Addad and Kanade
- Copyright date:
- 2017
- Notes:
- This is the accepted manuscript version of the article. The final version is available online from PMLR at: http://proceedings.mlr.press/v54/cohen-addad17a.html
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record