- Machine learning theory
- Societal aspects of machine learning; fairness in ML; interpretability in ML
Ruth Urner has joint the EECS department at York University as an assistant professor in 2017. She currently is also a faculty affiliate at the Vector Institute. Previously, she was a senior research scientist at the Max Planck Institute for intelligent systems in Tübingen, Germany, and a postdoctoral fellow at Carnegie Mellon’s Machine Learning department as well as at Georgia Tech. She received her PhD from the University of Waterloo for a thesis on statistical learning theory in 2013.
Her research develops mathematical tools and frameworks for analyzing the possibilities and limitations of automated learning, with a focus on semi-supervised, active and transfer learning. Currently is is particularly interested developing formal foundations for topics relating to societal impacts of machine learning, such as human interpretability and fairness in machine learning.
She regularly serves as a senior program committee member of the major machine learning conferences, such as NeurIPS, ICML, AISTATS and COLT.
- Christina Göpfert, Shai Ben-David, Olivier Bousquet, Sylvain Gelly, Ilya O. Tolstikhin, Ruth Urner: When can unlabeled data improve the learning rate? Proceedings of the 32nd Conference on Learning Theory (COLT) 2019.
- Aryeh Kontorovich, Sivan Sabato, Ruth Urner: Active Nearest-Neighbor Learning in Metric Spaces. Journal of Machine Learning Research (JMLR) 18(195): 1–38, 2018.
- Anastasia Pentina, Ruth Urner: Lifelong Learning with Weighted Majority Votes. Proceedings of the 30th Annual Conference on Neural Information Processing Systems (NIPS) 2016.
- Shai Ben-David, Ruth Urner: On Version Space Compression. Proceedings of the 27th International Conference on Algorithmic Learning Theory (ALT) 2016.
- Christopher Berlind, Ruth Urner: Active Nearest Neighbors in Changing Environments. Proceedings of the 32nd International Conference on Machine Learning (ICML) 2015.
- Maria-Florina Balcan, Amit Daniely, Ruta Mehta, Ruth Urner, Vijay V. Vazirani: Learning economic parameters from revealed preferences. Proceedings of the 10th International Conference Web and Internet Economics (WINE) 2014.
- Ruth Urner, Sharon Wulff, Shai Ben-David: PLAL: Cluster-Based Active Learning. Proceedings of the 26th Conference on Learning Theory (COLT) 2013.
- Ruth Urner, Shai Ben-David, Shai Shalev-Shwartz: Access to Unlabeled Data can Speed up Prediction Time. Proceedings of the 28th International Conference on Machine Learning (ICML) 2011.