COLT
1999
Springer
14 years 3 months ago
1999
Springer
COLT
1999
Springer
14 years 3 months ago
1999
Springer
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...
COLT
1999
Springer
14 years 3 months ago
1999
Springer
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 ...
COLT
1999
Springer
14 years 3 months ago
1999
Springer
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...
COLT
1999
Springer
14 years 3 months ago
1999
Springer
COLT
1999
Springer
14 years 3 months ago
1999
Springer
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 ...
COLT
1999
Springer
14 years 3 months ago
1999
Springer
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...
COLT
1999
Springer
14 years 3 months ago
1999
Springer
—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...
COLT
1999
Springer
14 years 3 months ago
1999
Springer
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...
COLT
1999
Springer
14 years 3 months ago
1999
Springer