Dylan Foster receives Best Paper and Best Student Paper awards at COLT 2019

Dylan Foster, Postdoctoral Researcher with the MIT Institute for Foundations of Data Science (MIFODS) and Postdoctoral Associate of both IDSS and SDSC, received the best paper award at the Conference on Learning Theory (COLT) 2019 for “Statistical Learning with a Nuisance Component.” Foster also received a best student paper award for “The Complexity of Making the Gradient Small in Stochastic Convex Optimization.”

The Conference on Learning Theory (COLT) is part of the ACM Federated Computing Research Conference (FCRC). FCRC organized a wide range of conferences and workshops, featuring topics of broad appeal to the computing research community into a week-long event. This model facilitates communication among researchers in different fields in computer science and engineering.

Foster is interested in in all aspects of generalization, sample complexity, and related algorithmic problems, especially for real-world problems such as interactive learning, deep learning, and non-convex learning.