16188 search results - page 5 / 3238 » The Optimal PAC Algorithm |
IPL
2010
13 years 6 months ago
2010
We study the problem of learning parity functions that depend on at most k variables (kparities) attribute-efficiently in the mistake-bound model. We design a simple, deterministi...
VLSISP
2008
13 years 7 months ago
2008
The compiler is generally regarded as the most important software component that supports a processor design to achieve success. This paper describes our application of the open re...
ALT
1999
Springer
13 years 11 months ago
1999
Springer
We introduce a new model for learning in the presence of noise, which we call the Nasty Noise model. This model generalizes previously considered models of learning with noise. Th...
CORR
2006
Springer
13 years 7 months ago
2006
Springer
Abstract. We propose and analyze a new vantage point for the learning of mixtures of Gaussians: namely, the PAC-style model of learning probability distributions introduced by Kear...
FOCS
2006
IEEE
14 years 1 months ago
2006
IEEE
We give the first representation-independent hardness results for PAC learning intersections of halfspaces, a central concept class in computational learning theory. Our hardness...