BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260306T091832EST-1438akf0ui@132.216.98.100
DTSTAMP:20260306T141832Z
DESCRIPTION:Title: Hierarchical Clustering With Confidence\n\nAbstract: Hie
 rarchical clustering is one of the most widely used approaches for explori
 ng data. However\, its greedy nature makes it highly sensitive to small pe
 rturbations\, blurring the lines between genuine structure and spurious pa
 tterns.  In this work\, we show how randomizing hierarchical clustering ca
 n be useful not just for assessing clustering stability but also for desig
 ning valid hypothesis testing procedures based on clustering results.  In 
 particular\, we propose a method for constructing a valid p-value at each 
 node of the hierarchical clustering dendrogram that quantifies evidence ag
 ainst performing the greedy merge.  Furthermore\, we show how our p-values
  can be used to estimate the number of clusters\, with a probabilistic gua
 rantee on overestimation of the number of clusters.  This is joint work wi
 th Di Wu and Snigdha Panigrahi.\n\nSpeaker: Jacob Bien’s research focuses 
 on statistical machine learning and in particular the development of novel
  methods that balance flexibility and interpretability for analyzing compl
 ex data. He combines ideas from convex optimization and statistics to deve
 lop methods that are of direct use to scientists and others with large dat
 asets. His work has been supported by a NSF CAREER award\, a three-year NS
 F grant on high-dimensional covariance estimation\, an NIH R01 grant on me
 thods for multi-view data\, and grants from the Simons Foundation on devel
 oping new statistical methodology for oceanography. He is a fellow of the 
 Institute of Mathematical Statistics and a fellow of the American Statisti
 cal Association.  He serves as an associate editor of the Journal of the A
 merican Statistical Association\; he was previously an associate editor fo
 r the Journal of the Royal Statistical Society (Series B)\, Biometrika\, t
 he Journal of Computational and Graphical Statistics\, and Biostatistics. 
 Before joining USC\, he was an assistant professor at Cornell.\n\nhttps://
 mcgill.zoom.us/j/82441217734\n\nMeeting ID: 824 4121 7734\n\nPasscode: Non
 e\n
DTSTART:20260220T203000Z
DTEND:20260220T213000Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Jacob Bien (University of Southern California)
URL:/mathstat/channels/event/jacob-bien-university-sou
 thern-california-371293
END:VEVENT
END:VCALENDAR