Abstract--We give sublinear-time approximation algorithms for some optimization problems arising in machine learning, such as training linear classifiers and finding minimum enclos...
Kenneth L. Clarkson, Elad Hazan, David P. Woodruff
Abstract. This work extends studies of Angluin, Lange and Zeugmann on how learnability of a language class depends on the hypothesis space used by the learner. While previous studi...
Inspired by the results obtained in the string case, we present in this paper the extension of the correction queries to regular tree languages. Relying on Angluin’s and Sakakib...
Abstract. We prove that interactive learning based classical realizability (introduced by Aschieri and Berardi for first order arithmetic [1]) is sound with respect to Coquand game...
Data-driven function tag assignment has been studied for English using Penn Treebank data. In this paper, we address the question of whether such method can be applied to other la...