Grant: Canada Research Chairs

Machine learning often requires large amounts of potentially expensive data, a problem that is addressed by research on interactive learning. While classical machine learning models assume either randomly selected data or extremely inadequate data, interactive models assume carefully selected data, as is reasonable in a variety of applications. Dr. Zilles’ objective is to design and analyze formal models of interactive learning and to develop data-economical algorithms that can efficiently solve complex learning problems. The models and algorithmic techniques that Dr. Zilles and her research team provide may change the way machine learning is deployed. She is aiming at theoretical guarantees, but her long-term goal is to achieve improvements in applied machine learning as well.