Kai Wang is a doctoral candidate studying computer science at Harvard University. Credit: Kai Wang. All Rights Reserved.

Academics

CSRAI Symposium: Solving social challenges formulated as optimization problems

4:00 PM - 5:00 PM / February 22, 2022

UNIVERSITY PARK, Pa. — Kai Wang, a doctoral candidate studying computer science at Harvard University, will deliver a talk as part of the Young Achievers Symposium organized by the Center for Socially Responsible Artificial Intelligence. Wang's talk, “Decision-focused Learning: Integrating Optimization Problems into Training Pipeline to Resolve Social Challenges,” will be held at 4 p.m. on Tuesday, Feb. 22, via Zoom, and will be followed by a question-and-answer session.

About the talk

“Decision-focused Learning: Integrating Optimization Problems into Training Pipeline to Resolve Social Challenges”

This talk focuses on solving social challenges formulated as optimization problems with missing parameters. For example, wildlife conservation challenges are commonly modeled as game theory problems between patrollers and poachers with unknown utility functions. Health service scheduling problems are formulated as resource allocation problems with unknown intervention effectiveness. A common way to address missing information is to learn a predictive model to predict missing parameters from domain-specific features, where actionable decisions can be obtained from solving the optimization problems with predicted parameters. However, the predictive model is trained to maximize the predictive accuracy but not the performance of the chosen decisions, leading to a mismatch between the training and evaluation objectives. Wang's research focuses on addressing the issue of mismatch objectives by expressing optimization problems, including non-convex, multi-agent, and sequential problems, as differentiable layers to integrate into the training pipeline. This novel training method leads to decision-focused learning that learns the predictive model to directly optimize the performance of the proposed decisions. Lastly, the talk concludes with experimental results in various social challenges to demonstrate the performance boost led by decision-focused learning.

About the Speaker

Kai Wang is a doctoral candidate studying computer science at Harvard University working with Professor Milind Tambe. Wang graduated from National Taiwan University with a bachelor of science in math and electrical engineering, where he won two silver medals at the International Mathematical Olympiad. His work focuses on providing actionable decisions to solve wildlife conservation and healthcare challenges. Both domains are multi-agent systems that require using machine learning to address the uncertainty involved in the system and optimization to suggest actionable solutions. Wang identifies the issue of solving machine learning and optimization problems separately, where he proposes various new techniques to integrate optimization problems into the machine learning pipeline to achieve decision-focused learning.

About the Young Achievers Symposium

The Young Achievers Symposium, which will be held virtually throughout the spring, highlights early career researchers in diverse fields of AI for social impact and seeks to focus on emerging research, stimulate discussions, and initiate collaborations that can advance research in artificial intelligence for societal benefit.  

All events in the series are free and open to the public. Penn State students, postdoctoral scholars, and faculty with an interest in socially responsible AI applications are encouraged to attend. You can view the full symposium series schedule and watch recordings of past events on the CSRAI website

The series is organized by CSRAI Program Chair Amulya Yadav, PNC Career Development Assistant Professor in the College of Information Science and Technology. All the talks will be hosted by Hangzhi Guo, a second-year doctoral student in the College of IST.