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:20250407T111911
DTSTART;TZID=America/Detroit:20250520T090000
DTEND;TZID=America/Detroit:20250520T170000
SUMMARY:Exhibition:Carlo Vitale Exhibition
DESCRIPTION:Carlo Vitale is a distinguished Michigan-based artist whose vibrant contributions to the Detroit art scene have flourished since the 1970s. A native of Detroit\, Vitale's work is celebrated as part of the second generation of the Cass Corridor Art Movement\, Detroit’s first avante garde. His art draws inspiration from the sweeping vistas of farmland seen from above\, the intricate patterns of quilt-making\, the dynamic energy of cityscapes\, and the rich tapestry of daily life. Vitale eloquently characterizes his mesmerizing oil paintings and prints as “kinetic\, metaphysical abstractions\,” inviting viewers to engage with the depth and vitality of his creative vision.\n\nVitale received his Bachelor of Fine Arts and Masters of Fine Arts from Wayne State University in Detroit.  His work can be found in many collections including The Whitney Museum of Fine Art in New York\, The Detroit Institute of Art\, Cranbrook Art Museum\, Wayne State University Collection\, University of Michigan Museum of Art and corporate\, hospital\, and private collections throughout the country.
UID:134757-21874881@events.umich.edu
URL:https://events.umich.edu/event/134757
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Visual Arts,Humanities,Free,Exhibition,Detroit,Culture
LOCATION:North Campus Research Complex Building 18 - NCRC Galleries
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20250507T114034
DTSTART;TZID=America/Detroit:20250520T090000
DTEND;TZID=America/Detroit:20250520T110000
SUMMARY:Lecture / Discussion:Exploring Interpretable Latent Structure in Modern Data by Bayesian Modeling: Theory and Applications
DESCRIPTION:The increasing complexity of modern data necessitates flexible statistical approaches capable of uncovering various latent structures\, often intricately linked to population heterogeneity. This dissertation explores probabilistic models\, particularly latent variable models and hierarchical models\, within a Bayesian framework across various settings. It highlights their effectiveness in extracting meaningful patterns and representations from data\, while also deepening our theoretical and computational understanding of these models.\n\nThe first chapter develops models and theoretical insights for hierarchical topic models\, characterized by latent tree-structured topic hierarchies that yield a rich structure formed by multiple topic polytopes sharing faces. The second chapter builds on these geometric insights\, extending them to continuous convolutional kernels. In particular\, it sheds light on identifiability in general nonparametric mixtures of such distributions\, where each component is nearly supported on a low-dimensional affine subspace. The third chapter revisits topic models from a different angle\, exploring connections between Latent Dirichlet Allocation and mixtures of product multinomial models via tensor decomposition of the Dirichlet distribution. The fourth chapter examines general hierarchical models in grouped-data settings and extends strong identifiability theory from mixture models to these settings\, establishing inverse bounds tailored to specific asymptotic regimes. The fifth chapter develops a nonparametric spatio-temporal model for dynamic velocity fields\, with an emphasis on scalable inference. Finally\, the last chapter addresses Bayesian methods in sequential decision-making and provides regret guarantees for Thompson sampling in sparse linear contextual bandit problems by analyzing the posterior under dynamic environments.\n\nA recurring theme of this dissertation is the asymptotic analysis of the posterior distribution of model parameters. Parameter learning is significantly more challenging than density estimation for latent variable models\, often with complex dependencies across components. Nevertheless\, such analysis enhances interpretability and informs the performance of downstream tasks that incorporate these models. It also reveals structural properties that can be leveraged for efficient inference. Overall\, this dissertation bridges theoretical and practical aspects of Bayesian modeling and emphasizes its potential to extract interpretable structures from complex datasets.
UID:135498-21876888@events.umich.edu
URL:https://events.umich.edu/event/135498
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Dissertation
LOCATION:West Hall - 438
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20250211T122734
DTSTART;TZID=America/Detroit:20250520T090000
DTEND;TZID=America/Detroit:20250520T160000
SUMMARY:Exhibition:Redefining the Crown
DESCRIPTION:In Winter 2025\, the Lane Hall exhibit space will feature a portraiture series titled Redefining the Crown showcasing the powerful stories of six Black breast cancer survivors.\n\nBased on a photo essay by U-M Faculty Versha Pleasant (MD/MPH) and Ava Purkiss (PhD) in Medicine at Michigan\, this exhibition examines the cultural and personal significance of hair within Black communities\, particularly through the lens of breast cancer treatment and recovery. The term \"crown\" is deeply symbolic in Black culture\, signifying beauty\, strength\, and identity. The featured photo essay by photographer Tafari Stevenson-Howard captures the intimate journeys of Ann Chatman\, Tanisha Kennedy\, Felecia McDaniel\, Shantell Elaine McCoy\, Tamara Lynn Myles\, and Veleria Banks.\n\nThrough their narratives and portraits\, the exhibit examines how these women have navigated the profound impact of hair loss caused by chemotherapy\, inviting the audience to witness their stories with radical empathy. It explores the cultural pride and personal identity intricately tied to their hair\, and how these elements are redefined amidst their battles with breast cancer.\n\nThe exhibit will be on view from January 21\, 2025 to August 8\, 2025. This exhibition is presented with support from IRWG\, the Department of Women's and Gender Studies\, and Michigan Medicine. \n\nLocated on the first floor of Lane Hall (204 S. State Street)\, the Exhibit Space is free and open to the public\, M-F\, 9am-4pm.
UID:129602-21864137@events.umich.edu
URL:https://events.umich.edu/event/129602
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Art,women,african american,Women's And Gender Studies,institute for research on women and gender
LOCATION:Lane Hall
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20250328T143739
DTSTART;TZID=America/Detroit:20250520T090000
DTEND;TZID=America/Detroit:20250520T120000
SUMMARY:Workshop / Seminar:Talent Acquisition Bootcamp
DESCRIPTION:Course details and registration are available on the Organizational Learning website.
UID:133543-21873224@events.umich.edu
URL:https://events.umich.edu/event/133543
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Self Development,Leadership,Human Resources
LOCATION:Wolverine Tower - Suite 18 G048
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20250513T122307
DTSTART;TZID=America/Detroit:20250520T093000
DTEND;TZID=America/Detroit:20250520T110000
SUMMARY:Workshop / Seminar:CoderSpaces - Tuesdays
DESCRIPTION:Are you grappling with a piece of code\, trying to compute on a cluster\, or just getting started with a new method such as machine learning? Then we might have just the right space for you.\n\nAll members of the U-M community are invited to join our weekly virtual CoderSpaces to get research support and connect with others.\n\nTuesdays\, 9:30-11 a.m. ET\, via Zoom (Meeting ID:94181215786)\nWednesdays\, 1:30-3 p.m. ET\, via Zoom (Meeting ID: 98659357324)
UID:117253-21865831@events.umich.edu
URL:https://events.umich.edu/event/117253
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Social Sciences,Social Science,Machine Learning,Data Science,Data Management,Data Linkage,Data Curation,Data Collection,Data Analysis,Data
LOCATION:
CONTACT:
END:VEVENT
END:VCALENDAR