From on-line to batch learning
COLT '89 Proceedings of the second annual workshop on Computational learning theory
Separating Distribution-Free and Mistake-Bound Learning Models over the Boolean Domain
SIAM Journal on Computing
Machine Learning
Machine Learning
Secure Human Identification Protocols
ASIACRYPT '01 Proceedings of the 7th International Conference on the Theory and Application of Cryptology and Information Security: Advances in Cryptology
On-line Algorithms in Machine Learning
Developments from a June 1996 seminar on Online algorithms: the state of the art
The complexity of approximate counting
STOC '83 Proceedings of the fifteenth annual ACM symposium on Theory of computing
On noise-tolerant learning of sparse parities and related problems
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
| Hi-index | 0.89 |
We study the problem of learning parity functions that depend on at most k variables (k-parities) attribute-efficiently in the mistake-bound model. We design a simple, deterministic, polynomial-time algorithm for learning k-parities with mistake bound O(n^1^-^1^k). This is the first polynomial-time algorithm to learn @w(1)-parities in the mistake-bound model with mistake bound o(n). Using the standard conversion techniques from the mistake-bound model to the PAC model, our algorithm can also be used for learning k-parities in the PAC model. In particular, this implies a slight improvement over the results of Klivans and Servedio (2004) [1] for learning k-parities in the PAC model. We also show that the O@?(n^k^/^2) time algorithm from Klivans and Servedio (2004) [1] that PAC-learns k-parities with sample complexity O(klogn) can be extended to the mistake-bound model.