Faculty Recruiting Support CICS

AI-Driven Experimental Design for Accelerating Science and Engineering

01 Mar
Wednesday, 03/01/2023 12:00pm to 1:00pm
Computer Science Building, Room 150/151
Seminar

Title: AI-Driven Experimental Design for Accelerating Science and Engineering

Abstract: AI-driven experimental design methods have the potential to accelerate costly discovery and optimization tasks throughout science and engineering--from materials design and drug discovery to computer systems tuning and instrument control. These methods are promising as they provide the intelligent decision making needed for use in complex real-world problems where experiments are time-consuming or expensive, and efficiency is paramount. In the first part of my talk, I will discuss challenges that I encountered while applying these methods to new types of scientific optimization problems being pursued at national labs. I will then introduce an information-based framework for flexible experimental design, which overcomes these challenges by enabling easy customization to new problem settings. This framework is theoretically principled, and has been used by scientists for efficient materials synthesis and optimization in large scientific instruments. Along the way, I will discuss my vision for reliable systems that expand the scope of AI-driven experimental design, and make it easier to use, so that it can be put in the hands of scientists, engineers, and other practitioners everywhere.

Bio: Willie Neiswanger is a postdoctoral scholar in the Computer Science Department at Stanford University. Previously, he completed his PhD in machine learning at Carnegie Mellon University. He develops machine learning techniques to perform optimization and experimental design in costly real-world settings, where resources are limited. His work spans topics in active learning, uncertainty quantification, Bayesian decision making, and reinforcement learning, and he applies these methods downstream to solve problems in science and engineering. Willie's work has received honors including a Best Paper Award at OSDI'21, and has been published in top machine learning venues (e.g., NeurIPS, ICML, ICLR, AAAI, AISTATS) and natural science journals (e.g., J Chem Physics, J Immunology, Cell Reports, Nucl Fusion). He has also collaborated with the SLAC National Accelerator Laboratory and the Princeton Plasma Physics Laboratory, where his methods have been run live on particle accelerators and tokamak machines for tuning/control tasks.

 

 

Faculty host
: