Past talk · AI/ML Seminar Series
Ideal made real: machine learning with limited data and interpretable outputs
Postdoctoral Researcher, Microsoft Research New England
- Date & time
- Monday, May 10, 2021 · 1:00 PM
- Location
- Online (live stream)
Abstract
Success stories in machine learning tend to be concentrated on ideal scenarios where clean labeled data are abundant and constraints are rare. But machine learning in practice is rarely so pristine. In this talk we explore how to reconcile these along two axes: learning with scarce or heterogeneous data, and making complex models interpretable. First, I present approaches for amplifying datasets based on the theory of Optimal Transport, with applications in machine translation, transfer learning, and dataset shaping. Second, I present work on designing methods to extract explanations from complex models and a novel framework for interpretable machine learning inspired by the study of human explanation in the social sciences.
About the speaker
David Alvarez-Melis is a postdoctoral researcher in the Machine Learning and Statistics Group at Microsoft Research, New England. He obtained a Ph.D. in computer science from MIT advised by Tommi Jaakkola, and holds mathematics degrees from ITAM and the Courant Institute (NYU).