Machine Learning Across Disciplines: New Theoretical Developments
To gather the best minds working on Big Data, the Incubator hosted a large convening on June 23, 2022: Machine Learning Across Disciplines: New Theoretical Developments. We were excited to be back in-person after two years of remote work and difficulty traveling, and we were especially thrilled to host an event at the new David Rubenstein Forum.
Machine learning methods have revolutionized modern data analysis. This conference brought together researchers from different disciplines – statistics, computer science, and econometrics – to discuss recent advances in our understanding of the theory underlying these methods, emphasizing theoretical guarantees on their performance. A primary goal of the conference was to foster interactions across researchers in different areas, thereby deepening our understanding of current methods and providing conceptual tools for the development of new ones.
The following speakers discussed new work in their respective fields of expertise:
Adel Javanmard, University of Southern California
Stefan Wager, Stanford University
Misha Belkin, University of California San Diego
Denis Chetverikov, UCLA
Whitney Newey, MIT
Jianqing Fan, Princeton University
Huibin (Harry) Zhou, Yale University
Robert Nowak, University of Wisconsin
Vasilis Syrgkanis, Microsoft
Tengyu Ma, Stanford University