Date:
Location:
Talk title: A unified framework for robustness, fairness, and collaboration in machine learning
“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 presence of everyday economic forces and the integrity of 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), a large-scale mentoring and community building initiative for the theory of machine learning community. Among her honors are an NSF CAREER award, NeurIPS and ICAPS best paper awards, an EC exemplary in AI track award, and several industry awards and fellowships.”