National Center for Supercomputing Applications WordPress Master Calendar

Back to Listing

NCSA staff who would like to submit an item for the calendar can email

Confidently Scaling Optimization

Event Type
Sponsor Digital Transformation Institute
Nov 3, 2022   3:00 - 4:00 pm  
John Duchi, Associate Professor of Statistics and Electrical Engineering, Stanford University
Contact Digital Transformation Institute
Originating Calendar
NCSA External Events Feed

With the maturing of AI and multi-agent systems research, we have a tremendous opportunity to direct these advances towards addressing complex societal problems. I will focus on domains of public health and conservation and address one key cross-cutting challenge: how to effectively deploy our limited intervention resources in these problem domains. I will present results from work around the globe using AI for challenges such as HIV prevention, maternal and child care interventions, and as well as wildlife conservation. Achieving social impact in these domains often requires methodological advances. To that end, I will highlight key research advances in multi-agent reasoning and learning, in particular in restless multi-armed bandits, influence maximization in social networks, computational game theory, and decision-focused learning. In pushing this research agenda, our ultimate goal is to facilitate local communities and non-profits to directly benefit from advances in AI tools and techniques.

John Duchi is an associate professor of statistics and electrical engineering and (by courtesy) computer science at Stanford University. His work spans statistical learning, optimization, information theory, and computation, with a few driving goals: 1) To discover statistical learning procedures that optimally trade between real-world resources – computation, communication, privacy provided to study participants – while maintaining statistical efficiency; 2) To build efficient large-scale optimization methods that address the spectrum of optimization, machine learning, and data analysis problems we face, allowing us to move beyond bespoke solutions to methods that robustly work; 3) To develop tools to assess and guarantee the validity of, and the confidence we should have in, machine-learned systems. Of many honors and awards, he has won the SIAM SIGEST award for “an outstanding paper of general interest” and best papers at the Neural Information Processing Systems conference and International Conference on Machine Learning; Early Career Prize in Optimization from the Society for Industrial and Applied Mathematics; Office of Naval Research Young Investigator Award; NSF CAREER award; Sloan Fellowship in Mathematics; Okawa Foundation Award; and UC Berkeley’s Ramamoorthy Distinguished Research Award.

link for robots only