We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...
Statistical learning theory chiefly studies restricted hypothesis classes, particularly those with finite Vapnik-Chervonenkis (VC) dimension. The fundamental quantity of interest i...
We present an improvement of Noviko 's perceptron convergence theorem. Reinterpreting this mistakebound as a margindependent sparsity guarantee allows us to give a PAC{style ...
Thore Graepel, Ralf Herbrich, Robert C. Williamson
Abstract. We establish a generic theoretical tool to construct probabilistic bounds for algorithms where the output is a subset of objects from an initial pool of candidates (or mo...
Generalization bounds depending on the margin of a classifier are a relatively recent development. They provide an explanation of the performance of state-of-the-art learning syste...