I am working on advancing the mathematical foundations of Machine Learning to apply to modern challenges of data analysis. I am particularly interested in analyzing what kind of benefits and information we can extract from unlabelled labelled data (eg in semi-supervised or active learning) or data from that came from diverse sources (eg in transfer learning).
In Proceedings of the 32nd International Conference on Machine Learning, 37, pages: 1870-1879, JMLR Workshop and Conference Proceedings, (Editors: Bach, F. and Blei, D. ), JMLR, ICML, 2015 (inproceedings)
Urner, R., Wulff, S., Ben-David, S.
PLAL: Cluster-based active learning
In Proceedings of the 26th Annual Conference on Learning Theory, 30, pages: 376-397, (Editors: Shalev-Shwartz, S. and Steinwart, I.), JMLR, COLT, 2013 (inproceedings)
Wulff, S., Urner, R., Ben-David, S.
In Proceedings of the 30th International Conference on Machine Learning, 28, pages: 145-153, (Editors: Dasgupta, S. and McAllester, D.), JMLR, ICML, 2013 (inproceedings)
In Algorithmic Learning Theory - 23rd International Conference, 7568, pages: 139-153, Lecture Notes in Computer Science, (Editors: Bshouty, NH. and Stoltz, G and Vayatis, N and Zeugmann, T), Springer Berlin Heidelberg, ALT, 2012 (inproceedings)
Urner, R., Ben-David, S., Shamir, O.
Learning from Weak Teachers
In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics, 22, pages: 1252-1260, (Editors: Lawrence, N. and Girolami, M.), JMLR, AISTATS, 2012 (inproceedings)
Swanson, C., Urner, R., Lank, E.
Naı̈ve Security in a Wi-Fi World
In Trust Management IV - 4th IFIP WG 11.11 International Conference Proceedings, pages: 32-47, (Editors: Nishigaki, M., Josang, A., Murayama, Y., Marsh, S.), IFIPTM, 2010 (inproceedings)
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems