National Center for Supercomputing Applications WordPress Master Calendar

View Full Calendar

NCSA staff who would like to submit an item for the calendar can email newsdesk@ncsa.illinois.edu.

Two Surprises When Optimization Meets Machine Learning

Event Type
Seminar/Symposium
Sponsor
C3.ai Digital Transformation Institute
Date
Sep 1, 2022   3:00 - 4:00 pm  
Speaker
Suvrit Sra, Associate Professor of Electrical Engineering and Computer Science, Massachusetts Institute of Technology
Registration
required.
Contact
C3.ai Digital Transformation Institute
Views
9
Originating Calendar
C3.ai DTI Events Calendar

It is well-known that there are large gaps between optimization theory and machine learning practice. However, there are two even more surprising gaps that have persisted at the fundamental level. The first one arises from ignoring the elephant in the room: non-differentiable non-convex optimization, e.g., when training a deep ReLU network. The second surprise is more disturbing: it uncovers a non-convergence phenomenon in the training of deep networks, and as a result it challenges existing convergence theory and training algorithms. Both these fundamental surprises open new directions of research, and we talk about some of our theoretical progress on these, as well as potential research questions.

Suvrit Sra is an associate professor in MIT’s EECS Department; a core faculty member of the Institute for Data, Systems, and Society (IDSS) and at the Laboratory for Information and Decision Systems (LIDS); and a member of MIT-ML and Statistics groups. He earned his PhD in Computer Science from the University of Texas at Austin. Before moving to MIT, he was a Senior Research Scientist at the Max Planck Institute for Intelligent Systems, in Tübingen, Germany. His research lies at the intersection of machine learning with mathematics, spanning areas such as differential geometry, matrix analysis, convex analysis, probability theory, and optimization. He founded the Optimization for Machine Learning (OPT) series of workshops in 2008 (at NeurIPS). He is a co-founder and chief scientist of macro-eyes, a global OR+ OPT+ ML+ healthcare startup.

link for robots only