We study the properties of the agnostic learning framework of Haussler [Hau92] and Kearns, Schapire and Sellie [KSS94]. In particular, we address the question: is there any situat...
Previous work on Natural Language Processing for Information Retrieval has shown the inadequateness of semantic and syntactic structures for both document retrieval and categoriza...
—There are many calls for innovative learning methods that utilize advanced technologies. However, we will raise fundamental questions that look deep into the future of the educa...
Experimental assessment of the performance of classification algorithms is an important aspect of their development and application on real-world problems. To facilitate this analy...
Many works have shown that strong connections relate learning from examples to regularization techniques for ill-posed inverse problems. Nevertheless by now there was no formal ev...
Lorenzo Rosasco, Andrea Caponnetto, Ernesto De Vit...