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:20260105T093408
DTSTART;TZID=America/Detroit:20260130T100000
DTEND;TZID=America/Detroit:20260130T110000
SUMMARY:Social / Informal Gathering:La Tertulia: Spanish Coffee Hour
DESCRIPTION:Hola! ¿Cómo estás?\n\n-Practice your Spanish-speaking skills with peers & instructors in a relaxed environment. All language levels and students are welcome to join the conversation.\n\n-Come & go as you please\, stay as little or as long as you would like!\n\n-Free coffee\, tea\, light snacks\, & baked goods.\n\nThe RLL Commons is located in the center hallway of the 4th floor of the Modern Languages Building.\n\nFor more information contact Julie Harrell at (harrelju@umich.edu).
UID:143170-21892360@events.umich.edu
URL:https://events.umich.edu/event/143170
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Coffee,Undergraduate Students,Undergraduate,Study Abroad,Spanish,Spain,Social,Romance Languages And Literatures,Networking,Latin America,Languages,Language,International,Intercultural,Games,Free,Food,European,Europe,Engaged Learning,Culture,Community Engagement,Community,Central America
LOCATION:Modern Languages Building - RLL Commons, 4314 MLB
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260119T101618
DTSTART;TZID=America/Detroit:20260130T100000
DTEND;TZID=America/Detroit:20260130T110000
SUMMARY:Workshop / Seminar:Statistics Department Seminar Series: Pierre Bellec\, Associate Professor\, Department of Statistics\, Rutgers University
DESCRIPTION:Abstract: The talk will explore properties of the iterates obtained from iterative algorithms in high-dimensional linear regression problems\, in the regime where the feature dimension is comparable with the sample size.  Examples of common iterative algorithms covered by the analysis include Gradient Descent (GD)\, proximal GD and their accelerated variants such as Fast Iterative Soft-Thresholding (FISTA)\, as well as Stochastic Gradient Descent (SDG). For these estimators\, we will introduce estimators for the generalization error of the iterate for any fixed iteration along the trajectory. These estimators are proved to be root-n consistent under Gaussian designs.  Applications to early-stopping are provided: when the generalization error of the iterates is a U-shape function of the iterations\, the estimates allow to select from the data an iteration that achieves the smallest generalization error along the trajectory.  Time permitting\, we will introduce debiasing corrections and valid confidence intervals for the components of the true coefficient vector from the iterate at any finite iteration.
UID:143257-21892564@events.umich.edu
URL:https://events.umich.edu/event/143257
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:seminar
LOCATION:West Hall - 340
CONTACT:
END:VEVENT
END:VCALENDAR