Login with HarvardKey to view all events.

A Unified Framework for Robustness, Fairness, and Collaboration in Machine Learning by Dr. Nika Haghtalab at CRCS Social Impact Seminar Series

This is a past event.

Monday, September 11, 2023 11am to 12pm

Nika Haghtalab, PHD headshot

Event Dates

Monday, September 11, 2023 11am to 12pm

Science and Engineering Complex (SEC), 2.112 View map

150 Western Ave. Allston, MA 02134

https://crcs.seas.harvard.edu/event/nika-haghtalab
View map Add to calendar

“Pervasive needs for robustness, multi-agent collaboration, and fairness have motivated the design of new methods in research and development. However, these methods remain largely stylized, lacking a foundational perspective and provable performance. In this talk, I will introduce and highlight the importance of multi-objective learning as a unifying paradigm for addressing these needs. This paradigm aims to optimize complex and unstructured objectives from only a small amount of sampled data. I will also discuss how the multi-objective learning paradigm relates to the classical and modern considerations in machine learning broadly, introduce technical tools with versatile provable guarantees, and empirical evidence for its performance on a range of important benchmarks.”

Event Details