On a bilevel optimization approach to fair classification
April 15, 2022, ESB 2001
Kangwook Lee
University of Wisconsin , Electrical and Computer Engineering
Abstract
The pandemic exacerbated inequities faced by people with disabilities and healthcare workers — both are at high risk of adverse physical and mental health outcomes. Robots alone are not going to fix these major societal problems; however, our work explores how we can design technology to lessen the burden of systemic ableism and healthcare system stress. I will discuss several of our recent projects in acute care and community health contexts. In acute care, we are building hospital-based robots to support the clinical workforce, to support item delivery, telemedicine, and decision support. In community health, we are creating interactive and adaptive systems that aim to extend the reach of cognitive neurorehabilitative therapies, provide respite to overburdened caregivers, and explore how technology might serve as a means for mediating positive interactions during hardship. We focus on building robots that can adaptively team with and longitudinally learn from people, and personalize and tailor their behavior.
Speaker's Bio
Kangwook Lee is an Assistant Professor at the Electrical and Computer Engineering department and the Computer Sciences department (by courtesy) at the University of Wisconsin-Madison. His research interests lie in trustworthy and scalable machine learning algorithms and systems using tools from information theory and coding.