COLT
2005
Springer
14 years 2 months ago
2005
Springer
Abstract. We present several results related to ranking. We give a general margin-based bound for ranking based on the L∞ covering number of the hypothesis space. Our bound sugge...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
In recent work Long and Servedio [LS05] presented a “martingale boosting” algorithm that works by constructing a branching program over weak classifiers and has a simple anal...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
We present a general decomposition algorithm that is uniformly applicable to every (suitably normalized) instance of Convex Quadratic Optimization and efficiently approaches an o...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
We present a new generalization bound where the use of unlabeled examples results in a better ratio between training-set size and the resulting classifier’s quality and thus red...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
COLT
2005
Springer
14 years 2 months ago
2005
Springer
We give a compression scheme for any maximum class of VC dimension d that compresses any sample consistent with a concept in the class to at most d unlabeled points from the domain...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
We examine a Markovian model for the price evolution of a stock, in which the probability of local upward or downward movement is arbitrarily dependent on the current price itself...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
We present two new methods for obtaining generalization error bounds in a semi-supervised setting. Both methods are based on approximating the disagreement probability of pairs of ...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
In the machine learning community it is generally believed that graph Laplacians corresponding to a finite sample of data points converge to a continuous Laplace operator if the s...
COLT
2005
Springer
14 years 2 months ago
2005
Springer
We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...