Sciweavers

40 search results - page 3 / 8
» A New PAC Bound for Intersection-Closed Concept Classes
Sort
View
ML
2007
ACM
108views Machine Learning» more  ML 2007»
13 years 5 months ago
Unconditional lower bounds for learning intersections of halfspaces
We prove new lower bounds for learning intersections of halfspaces, one of the most important concept classes in computational learning theory. Our main result is that any statist...
Adam R. Klivans, Alexander A. Sherstov
COLT
2006
Springer
13 years 9 months ago
Efficient Learning Algorithms Yield Circuit Lower Bounds
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
Lance Fortnow, Adam R. Klivans
ICC
2007
IEEE
13 years 12 months ago
A New Cooperative Strategy for Deafness Prevention in Directional Ad Hoc Networks
— We propose the novel concept of cooperation for deafness prevention in directional antenna ad hoc networks, along with a low-complexity multiuser detector specialised for these...
Andrea Munari, Francesco Rossetto, Michele Zorzi
ECML
1993
Springer
13 years 9 months ago
Complexity Dimensions and Learnability
In machine learning theory, problem classes are distinguished because of di erences in complexity. In 6 , a stochastic model of learning from examples was introduced. This PAClear...
Shan-Hwei Nienhuys-Cheng, Mark Polman
FOCS
1990
IEEE
13 years 9 months ago
Separating Distribution-Free and Mistake-Bound Learning Models over the Boolean Domain
Two of the most commonly used models in computational learning theory are the distribution-free model in which examples are chosen from a fixed but arbitrary distribution, and the ...
Avrim Blum