Many of the classification algorithms developed in the machine learning literature, including the support vector machine and boosting, can be viewed as minimum contrast methods that minimize a convexâ€¦ (More)

We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empiricalâ€¦ (More)

ence exists between parametric and nonparametric statistical tests. Parametric tests are only valid if the data satisfy certain assumptions. If these assumptions hold, they will, however, typicallyâ€¦ (More)

We give upper bounds on the Vapnik-Chervonenkis dimension and pseudodimension of two-layer neural networks that use the standard sigmoid function or radial basis function and have inputs from {D,â€¦ (More)

We examine the relationship between the VC dimension and the number of parameters of a threshold smoothly parameterized function class. We show that the VC dimension of such a function class is atâ€¦ (More)

The goal of machine learning is to learn unknown concepts from data. In real-world applications such as bioinformatics and computer vision, data frequently arises from multiple heterogeneous sourcesâ€¦ (More)

We consider online linear regression: at each round, an adversary reveals a covariate vector, the learner predicts a real value, the adversary reveals a label, and the learner suffers the squaredâ€¦ (More)