Please use this identifier to cite or link to this item:
https://doi.org/10.1109/18.915700
| Title: | The one-inclusion graph algorithm is near-optimal for the prediction model of learning | Authors: | Li, Y. Long, P.M. Srinivasan, A. |
Keywords: | Computational learning One-inclusion graph algorithm Prediction model Sample complexity Vapnik-Chervonenkis (VC) dimension |
Issue Date: | 2001 | Citation: | Li, Y., Long, P.M., Srinivasan, A. (2001). The one-inclusion graph algorithm is near-optimal for the prediction model of learning. IEEE Transactions on Information Theory 47 (3) : 1257-1261. ScholarBank@NUS Repository. https://doi.org/10.1109/18.915700 | Abstract: | Haussler, Littlestone, and Warmuth described a general-purpose algorithm for learning according to the prediction model, and proved an upper bound on the probability that their algorithm makes a mistake in terms of the number of examples seen and the Vapnik-Chervonenkis (VC) dimension of the concept class being learned. We show that their bound is within a factor of 1 + o(1) of the best possible such bound for any algorithm. | Source Title: | IEEE Transactions on Information Theory | URI: | http://scholarbank.nus.edu.sg/handle/10635/43369 | ISSN: | 00189448 | DOI: | 10.1109/18.915700 |
| 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.