Sciweavers

19 search results - page 2 / 4
» colt 2001
Sort
View
COLT
2001
Springer
13 years 10 months ago
Intrinsic Complexity of Learning Geometrical Concepts from Positive Data
Intrinsic complexity is used to measure the complexity of learning areas limited by broken-straight lines (called open semi-hulls) and intersections of such areas. Any strategy le...
Sanjay Jain, Efim B. Kinber
COLT
2001
Springer
13 years 10 months ago
Learning Rates for Q-Learning
In this paper we derive convergence rates for Q-learning. We show an interesting relationship between the convergence rate and the learning rate used in Q-learning. For a polynomi...
Eyal Even-Dar, Yishay Mansour
COLT
2001
Springer
13 years 10 months ago
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we ...
Peter L. Bartlett, Shahar Mendelson
COLT
2001
Springer
13 years 10 months ago
Learning Monotone DNF from a Teacher That Almost Does Not Answer Membership Queries
We present results concerning the learning of Monotone DNF (MDNF) from Incomplete Membership Queries and Equivalence Queries. Our main result is a new algorithm that allows effici...
Nader H. Bshouty, Nadav Eiron
COLT
2001
Springer
13 years 10 months ago
Learning Additive Models Online with Fast Evaluating Kernels
Abstract. We develop three new techniques to build on the recent advances in online learning with kernels. First, we show that an exponential speed-up in prediction time per trial ...
Mark Herbster