Time+Place: | Tuesday 10/05/2016 14:30 Room 337-8 Taub Bld. |

Title: | Unsupervised Ensemble Learning |

Speaker: | Boaz Nadler - COLLOQUIUM LECTURE http://www.wisdom.weizmann.ac.il/~nadler/ |

Affiliation: | Department of Computer Science and Applied Mathematics, Weizmann Institute of Science |

Host: | Nir Ailon |

In various applications, one is given the advice or predictions of several classifiers of unknown reliability, over multiple questions or queries. This scenario is different from the standard supervised setting where classifier accuracy can be assessed from available labeled training or validation data, and raises several questions: given only the predictions of several classifiers of unknown accuracies, over a large set of unlabeled test data, is it possible to a) reliably rank them, and b) construct a meta-classifier more accurate than any individual classifier in the ensemble? In this talk we'll show that under various independence assumptions between classifier errors, this high dimensional data hides simple low dimensional structures. In particular, we'll present simple spectral methods to address the above questions, and derive new unsupervised spectral meta-learners. We'll prove these methods are asymptotically consistent when the model assumptions hold, and also present their empirical success on a variety of unsupervised learning problems. Short bio: Boaz Nadler is an associate professor at the department of computer science and applied mathematics at the Weizmann Institute of Science. He holds a phd from Tel-Aviv university, spent 3 years at the applied math group at Yale university as a Gibbs assistant professor as well as a sabbatical year at Berkeley and Stanford. His research interests are in statistical machine learning, mathematical statistics and applications in optics, signal and image processing. Refreshments will be served from 14:15 Lecture starts at 14:30