Online Learning of Assignments
Abstract
Which ads should we display in sponsored search in order to maximize our revenue? How should we dynamically rank information sources to maximize the value of the ranking? These applications exhibit strong diminishing returns: Redundancy decreases the marginal utility of each ad or information source. We show that these and other problems can be formalized as repeatedly selecting an assignment of items to positions to maximize a sequence of monotone submodular functions that arrive one by one. We present an efficient algorithm for this general problem and analyze it in the no-regret model. Our algorithm possesses strong theoretical guarantees, such as a performance ratio that converges to the optimal constant of 1 1/e. We empirically evaluate our algorithm on two real-world online optimization problems on the web: ad allocation with submodular utilities, and dynamically ranking blogs to detect information cascades.
Additional Information
© 2010 Neural Information Processing Systems Foundation. This work was supported in part by Microsoft Corporation through a gift as well as through the Center for Computational Thinking at Carnegie Mellon, by NSF ITR grant CCR-0122581 (The Aladdin Center), and by ONR grant N00014-09-1-1044.Attached Files
Published - 3719-online-learning-of-assignments.pdf
Files
Name | Size | Download all |
---|---|---|
md5:d6f81f96da24c09179021fa2e123298d
|
250.2 kB | Preview Download |
Additional details
- Eprint ID
- 65822
- Resolver ID
- CaltechAUTHORS:20160331-163749460
- Microsoft Corporation
- Center for Computational Thinking, Carnegie Mellon
- CCR-0122581
- NSF
- N00014-09-1-1044
- Office of Naval Research (ONR)
- Created
-
2016-03-31Created from EPrint's datestamp field
- Updated
-
2020-03-09Created from EPrint's last_modified field
- Series Name
- Advances in Neural Information Processing Systems
- Series Volume or Issue Number
- 22