Please use this identifier to cite or link to this item:
https://doi.org/10.1006/inco.2000.2871
Title: | On-line learning with linear loss constraints | Authors: | Helmbold, D.P. Littlestone, N. Long, P.M. |
Issue Date: | 2000 | Citation: | Helmbold, D.P., Littlestone, N., Long, P.M. (2000). On-line learning with linear loss constraints. Information and Computation 161 (2) : 140-171. ScholarBank@NUS Repository. https://doi.org/10.1006/inco.2000.2871 | Abstract: | We consider a generalization of the mistake-bound model (for learning {0, 1}-valued functions) in which the learner must satisfy a general constraint on the number M+ of incorrect 1 predictions and the number M- of incorrect 0 predictions. We describe a general-purpose optimal algorithm for our formulation of this problem. We describe several applications of our general results, involving situations in which the learner wishes to satisfy linear inequalities in M+ and M-. © 2000 Academic Press. | Source Title: | Information and Computation | URI: | http://scholarbank.nus.edu.sg/handle/10635/39220 | ISSN: | 08905401 | DOI: | 10.1006/inco.2000.2871 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.