BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241118T130932
DTSTART;TZID=America/Detroit:20241122T100000
DTEND;TZID=America/Detroit:20241122T112000
SUMMARY:Workshop / Seminar:Stable matching as transportation
DESCRIPTION:We study matching markets with aligned preferences and establish a connection between common design objectives -- stability\, efficiency\, and fairness -- and the theory of optimal transport. Optimal transport gives new insights into the structural properties of matchings obtained from pursuing these objectives\, and into the trade-offs between different objectives. Matching markets with aligned preferences provide a tractable stylized model capturing supply-demand imbalances in a range of settings such as partnership formation\, school choice\, organ donor exchange\, and markets with transferable utility where bargaining over transfers happens after a match is formed.
UID:129230-21862354@events.umich.edu
URL:https://events.umich.edu/event/129230
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Economics,Microeconomics,seminar,Theory
LOCATION:Lorch Hall - 275D (in the MITRE Suite)
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20241114T135918
DTSTART;TZID=America/Detroit:20241122T100000
DTEND;TZID=America/Detroit:20241122T110000
SUMMARY:Workshop / Seminar:Statistics Department Seminar Series: Tianyu Zhang\, Postdoctoral Research Fellow\, Department of Statistics & Data Science\, Carnegie Mellon University.
DESCRIPTION:Abstract: Nonparametric procedures are frequently employed in predictive and inferential modeling to relate random variables without imposing specific parametric forms. In supervised learning\, for instance\, our focus is often on the conditional mean function that links predictive covariates to a numerical outcome of interest. While many existing statistical learning methods achieve this with optimal statistical performance\, their computational expenses often do not scale favorably with increasing sample sizes. This challenge is exacerbated in certain “online settings\,” where data is continuously collected and estimates require frequent updates.\n\nIn this talk\, I will discuss a class of nonparametric stochastic optimization methods. The estimates are constructed using stochastic gradient descent (SGD) over a function space of varying capacity. Combining this computational approach with compact function approximation strategies—such as utilizing eigenfunctions in a reproducing kernel Hilbert space—certain nonparametric estimators can attain both optimal statistical properties and minimal (computational) space expense. Additionally\, I will introduce a rolling validation procedure\, an online adaptation of cross-validation\, designed for hyperparameter tuning. This model selection process naturally integrates with incremental SGD algorithms\, imposing a negligible extra computational burden.\n\nhttps://terrytianyuzhang.github.io/
UID:124596-21853249@events.umich.edu
URL:https://events.umich.edu/event/124596
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:seminar
LOCATION:West Hall - 340
CONTACT:
END:VEVENT
END:VCALENDAR