Sciweavers

COLT
1999
Springer
13 years 11 months ago
On PAC Learning Using Winnow, Perceptron, and a Perceptron-like Algorithm
In this paper we analyze the PAC learning abilities of several simple iterative algorithms for learning linear threshold functions, obtaining both positive and negative results. W...
Rocco A. Servedio
COLT
1999
Springer
13 years 11 months ago
Drifting Games
We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the ...
Robert E. Schapire
COLT
1999
Springer
13 years 11 months ago
Boosting as Entropy Projection
We consider the AdaBoost procedure for boosting weak learners. In AdaBoost, a key step is choosing a new distribution on the training examples based on the old distribution and th...
Jyrki Kivinen, Manfred K. Warmuth
COLT
1999
Springer
13 years 11 months ago
On the Intrinsic Complexity of Learning Recursive Functions
Efim B. Kinber, Christophe Papazian, Carl H. Smith...
COLT
1999
Springer
13 years 11 months ago
On a Generalized Notion of Mistake Bounds
This paper proposes the use of constructive ordinals as mistake bounds in the on-line learning model. This approach elegantly generalizes the applicability of the on-line mistake ...
Sanjay Jain, Arun Sharma
COLT
1999
Springer
13 years 11 months ago
Multiclass Learning, Boosting, and Error-Correcting Codes
We focus on methods to solve multiclass learning problems by using only simple and efficient binary learners. We investigate the approach of Dietterich and Bakiri [2] based on er...
Venkatesan Guruswami, Amit Sahai
COLT
1999
Springer
13 years 11 months ago
Covering Numbers for Support Vector Machines
—Support vector (SV) machines are linear classifiers that use the maximum margin hyperplane in a feature space defined by a kernel function. Until recently, the only bounds on th...
Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Ro...
COLT
1999
Springer
13 years 11 months ago
Regret Bounds for Prediction Problems
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
Geoffrey J. Gordon
COLT
1999
Springer
13 years 11 months ago
Estimating a Mixture of Two Product Distributions
Yoav Freund, Yishay Mansour