BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Academic,Lectures & Speakers,Research
DESCRIPTION:Deep Distributional Learning with Non-crossing Quantile Network
 \n\nPlease join the GW Department of Statistics for a seminar with Hongtu Z
 hu\, PhD\, Kenan Distinguished Professor at the University of North Carolin
 a at Chapel Hill.\n\nAbstract:\n\nIn this talk\, we introduce a non-crossin
 g quantile (NQ) network for conditional distribution learning. By leveragin
 g non-negative activation functions\, the NQ network ensures that the learn
 ed distributions remain monotonic\, effectively addressing the issue of qua
 ntile crossing. Furthermore\, the NQ network-based deep distributional lear
 ning framework is highly adaptable\, applicable to a wide range of applicat
 ions\, from classical non-parametric quantile regression to more advanced t
 asks such as causal effect estimation and distributional reinforcement lear
 ning (RL). We also develop a comprehensive theoretical foundation for the d
 eep NQ estimator and its application to distributional RL\, providing an in
 -depth analysis that demonstrates its effectiveness across these domains. O
 ur experimental results further highlight the robustness and versatility of
  the NQ network.\n\nAbout the speaker:\n\nHongtu Zhu is the Kenan Distingui
 shed Professor of Biostatistics\, Statistics\, Radiology\, Computer Science
  and Genetics at the University of North Carolina at Chapel Hill. He was a 
 DiDi Fellow and Chief Scientist of Statistics at DiDi Chuxing between 2018 
 and 2020 and held the endowed Bao-Shan Jing Professorship in Diagnostic Ima
 ging at MD Anderson Cancer Center between 2016 and 2018. He is an internati
 onally recognized expert in statistical learning\, medical image analysis\,
  precision medicine\, biostatistics\, artificial intelligence and big data 
 analytics. He received an established investigator award from the Cancer Pr
 evention Research Institute of Texas in 2016\, the INFORMS Daniel H. Wagner
  Prize for Excellence in Operations Research Practice in 2019\, the ICSA 20
 25 Distinguished Achievement Award\, the IMS 2027 Medallion award and Lectu
 re and the COPSS 2025 Snedecor Award. He has published more than 350 papers
  in top journals\, including Nature\, Science\, Cell\, Nature Genetics\, Na
 ture Communication\, PNAS\, AOS\, Journal of the American Statistical Assoc
 iation (JASA)\, Biometrika and JRSSB\, as well as presenting 61+ conference
  papers at top conferences\, including meetings for Neurips\, ICLR\, ICML\,
  AAAI and KDD. He is the coordinating editor of JASA and the editor of JASA
  ACS.
DTEND:20260410T190000Z
DTSTAMP:20260508T144007Z
DTSTART:20260410T180000Z
GEO:38.899007;-77.049161
LOCATION:Duques Hall\, 152
SEQUENCE:0
SUMMARY:Statistics Seminar Series: Deep Distributional Learning with Non-cr
 ossing Quantile Network
UID:tag:localist.com\,2008:EventInstance_52086565474590
URL:https://calendar.gwu.edu/event/statistics-seminar-series-deep-distribut
 ional-learning-with-non-crossing-quantile-network
END:VEVENT
END:VCALENDAR