The Influence of Operational Cost on Estimation
Name
Rudin_The influence.pdf
Size
724.81 KB
Format
Adobe PDF
Checksum (MD5)
da961a96c0ee3f89d5ecc64db67d91c6
Author(s)
Tulabandhula, Theja
Rudin, Cynthia
Date Issued
January 2012
Journal
Proceedings of the 2012 International Symposium on Artificial Intelligence and Mathematics
Citation
Tulabandhula, Theja, and Cynthia Rudin. "The Influence of Operational Cost on Estimation." The 2012 International Symposium on Artificial Intelligence and Mathematics, Fort Lauderdale, Florida, January 9-11, 2012.
Version
Author's final manuscript
Abstract
This work concerns the way that statistical models are used to make decisions. In particular, we aim to merge the way estimation algorithms are designed with how they are used for a subsequent task. Our methodology considers the operational cost of carrying out a policy, based on a predictive model. The operational cost becomes a regularization term in the learning algorithm’s objective function, allowing either an optimistic or pessimistic view of possible costs. Limiting the operational cost reduces the hypothesis space for the predictive model, and can thus improve generalization. We show that different types of operational problems can lead to the same type of restriction on the hypothesis space, namely the restriction to an intersection of an l[subscript q] ball with a halfspace. We bound the complexity of such hypothesis spaces by proposing a technique that involves counting integer points in polyhedrons.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Sloan School of Management
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.cs.uic.edu/bin/view/Isaim2012/AcceptedPapers
