BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:EECS Faculty Candidate Seminar: Shibo Li 
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260711T182620Z
UID:tag:localist.com\,2008:EventInstance_45896795107020
DTSTART:20240319T150000Z
DTEND:20240319T160000Z
DESCRIPTION:Physics-Motivated and Inspired Probabilistic Learning\n\nAbstra
 ct:\n\nAI has emerged as the most transformative and revolutionary techniq
 ue\, reshaping many aspects of our lives. Its intersection with science\, 
 particularly physics\, has opened new avenues for understanding our world 
 and universe. This understanding is grounded in centuries of exploration b
 y brilliant minds. Physics studies today predominantly rely on rigorous me
 thods founded on universal physical laws. I will discuss integrating advan
 ced learning techniques\, notably Bayesian machine learning\, into computa
 tional physics in this presentation. This integration is crucial in an int
 erdisciplinary field that combines mathematics\, physics\, and computer sc
 ience to address meaningful\, real-world problems. As the first principle\
 , physics offers novel techniques and insights for tackling complex tasks 
 in complex\, structured data analysis. I envision synergizing physics and 
 probabilistic learning to create a formidable tool for exploring new front
 iers.\n\nBiography:\n\nShibo Li\, a fifth-year PhD candidate at the Univer
 sity of Utah\, is affiliated with the Kahlert School of Computing (SoC) an
 d the Scientific Computing and Imaging Institute (SCI). He earned his mast
 er's degree from the University of Pittsburgh and his bachelor's degree fr
 om the South China University of Technology. Li's research spans a range o
 f topics\, including Bayesian machine learning\, approximate inference\, i
 nteractive learning (encompassing Active Learning\, Bandits\, and Reinforc
 ement Learning)\, and high-dimensional spatial-temporal modeling. His PhD 
 thesis focuses on multi-fidelity modeling and optimization for physical si
 mulations. His works have been published in top-tier machine learning and 
 data mining avenues\, such as ICML\, NeurIPS\, ICLR\, AISTATS\, IJCAI\, an
 d CIKM. More information can be found on Li's page: https://imshibo.com/.
GEO:35.958178;-83.924516
LOCATION:Min H. Kao Electrical Engineering and Computer Science\, 435
SUMMARY:EECS Faculty Candidate Seminar: Shibo Li 
URL;VALUE=URI:https://calendar.utk.edu/event/eecs-faculty-candidate-seminar
 -shibo-li
CATEGORIES:Lectures & Presentations
END:VEVENT
END:VCALENDAR