Machine Learning/Duolingo Seminar - Nika Haghtalab

— 4:30pm

Location:
In Person and Virtual - ET - Gates Hillman 8102 and Zoom

Speaker:
NIKA HAGHTALAB, Assistant Professor, Department of Electrical Engineering and Computer Sciences, Co-director, Center for the Theoretical Foundations of Learning, Inference, Information, Intelligence, Mathematics and Microeconomics , University of California, Berkeley,
https://people.eecs.berkeley.edu/~nika/

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. 

— 

Nika Haghtalab is an Assistant Professor in the Department of Electrical Engineering and Computer Sciences at UC Berkeley. She works broadly on the theoretical aspects of machine learning and algorithmic economics. Prof. Haghtalab's work builds theoretical foundations for ensuring both the performance of learning algorithms in the presence of everyday economic forces and the integrity of the social and economic forces that are born out of the use of machine learning systems. 

She received her Ph.D. from the Computer Science Department of Carnegie Mellon University, where her thesis won the CMU School of Computer Science Dissertation Award (ACM nomination) and the SIGecom Dissertation Honorable Mention. She is a co-founder of Learning Theory Alliance (LeT-All). Among her honors are an NSF CAREER award, Sloan fellowship, Schmidt Sciences AI2050 fellowship, NeurIPS and ICAPS best paper awards, an EC exemplary in AI track award, and several industry awards and fellowships. 

In Person and Zoom Participation.  See announcement.

Add event to Google
Add event to iCal