A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. This class...
Rademacher and Gaussian complexities are successfully used in learning theory for measuring the capacity of the class of functions to be learned. One of the most important propert...
This paper presents an approach to automatically optimize the retrieval quality of ranking functions. Taking a Swarm Intelligence perspective, we present a novel method, SwarmRank...
Ernesto Diaz-Aviles, Wolfgang Nejdl, Lars Schmidt-...
We study the problem of PAC-learning Boolean functions with random attribute noise under the uniform distribution. We define a noisy distance measure for function classes and sho...
Nader H. Bshouty, Jeffrey C. Jackson, Christino Ta...
We present an approach for recovering articulated body pose from single monocular images using the Specialized Mappings Architecture (SMA), a non-linear supervised learning archit...