We develop a theory of online learning by defining several complexity measures. Among them are analogues of Rademacher complexity, covering numbers and fatshattering dimension fro...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
In this paper we present a new approach for measuring the relatedness between text segments, based on implicit semantic links between their words, as offered by a word thesaurus, n...
George Tsatsaronis, Iraklis Varlamis, Michalis Vaz...
The traditional co-training algorithm, which needs a great number of unlabeled examples in advance and then trains classifiers by iterative learning approach, is not suitable for ...
The performance of on-line algorithms for learning dichotomies is studied. In on-line learning, the number of examples P is equivalent to the learning time, since each example is ...