“Machine Learning: New Challenges and Connections”
AIR Distinguished Speaker Series
Maria-Florina Balcan, Assoc. Prof., Computer Science, Carnegie Mellon Univ.
When:
Monday, December 2, 2019
10:30am-11:00am networking and reception, 11:00am-12:00pm talk
Where:
Kilachand Center, 610 Commonwealth Ave, Colloquium Room 101
ABSTRACT:
Over the past decades, machine learning has evolved into a highly successful discipline that has significantly influenced several fields, including vision, information retrieval, and biology. Many of these advances are based on standard learning techniques where classifiers are trained based on large amounts of fully annotated data. As the field of machine learning is maturing, new opportunities await for fundamentally new training paradigms that could significantly broaden its impact and applicability. These include interactive learning procedures where the learning algorithm and the domain expert collaborate to facilitate most efficient learning without relying on massive amounts of human input, and techniques for learning much more complex objects beyond simple classifiers, such as computational procedures for solving hard combinatorial problems. In this talk, I will discuss recent advances in these directions.
BIO:
Maria-Florina Balcan is an Associate Professor in the School of Computer Science at Carnegie Mellon University. Her main research interests are machine learning, artificial intelligence, and theoretical computer science. She is a Sloan Fellow, a Microsoft Research New Faculty Fellow, a Kavli Fellow, and a recipient of an NSF CAREER award and several best paper awards. She currently serves as a program committee co-chair of the Neural Information Processing Systems 2020 conference, board member of the International Machine Learning Society, and general chair of the International Conference on Machine Learning 2021. She previously served as a program committee co-chair of the Conference on Learning Theory in 2014 and the International Conference on Machine Learning in 2016.