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:20260522T102454
DTSTART;TZID=America/Detroit:20260605T130000
DTEND;TZID=America/Detroit:20260605T150000
SUMMARY:Presentation:Learning with Quantum Examples: Multiclass\, Online\, and Smoothed Settings
DESCRIPTION:Abstract:\n\nAs quantum computing progresses toward fault-tolerant architectures\, the question of which computational tasks admit provable quantum advantages and which do not has become increasingly central. Learning theory\, and in particular learning from quantum examples\, provides one of the few settings in which unconditional quantum-classical separations can be established. In distribution-free (i.e.\, worst-case) PAC learning\, existing results show that quantum examples provide no asymptotic advantage in sample complexity. In contrast\, under the uniform distribution\, unbounded quantum-classical separations are known for learning Fourier-sparse Boolean functions. Together\, these results reveal a striking dichotomy. However\, this understanding has largely been developed in the context of learning Boolean functions in the batch setting\, leaving open how these phenomena extend more broadly. This thesis develops the theory of learning with quantum examples beyond the batch Boolean setting along three directions: multiclass learning\, online learning\, and smoothed learning.\n\nIn the multiclass PAC setting\, we establish upper and lower bounds on quantum sample complexity in both the realizable and agnostic regimes\, finding that quantum examples continue to yield no distribution-independent separation from classical examples\, with learning rates governed by the Natarajan dimension up to logarithmic factors in the label-space size. We next study online learning\, where no standard framework for learning with quantum examples existed prior to this work. We provide such a model by lifting the classical online framework to one in which the adversary provides distributions over labeled examples\, and then by encoding these distributions as quantum examples. We establish expected regret guarantees for binary and multiclass classification in both the realizable and agnostic settings. The central finding is that unrestricted adversarial power permits highly concentrated distributions that dequantize the learning problem. Motivated by this dequantization phenomenon\, we develop a smoothed learning framework that constrains distributions to be smooth\, interpolating between the concentrated-distribution regime\, in which no quantum advantage exists\, and the uniform-distribution regime\, in which unbounded separations are known. For the class of Fourier-sparse Boolean functions\, we show that such separations persist throughout a nontrivial near-uniform regime in both the batch and online settings.\n\nTogether\, these results paint a coherent picture of learning with quantum examples beyond the batch Boolean setting\, showing that quantum-classical separations depend on the interplay between hypothesis class structure\, distributional assumptions\, and the degree of adversarial control permitted in the learning process.
UID:148398-21904185@events.umich.edu
URL:https://events.umich.edu/event/148398
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Mathematics,Graduate Students,Graduate,Dissertation
LOCATION:East Hall - 3088
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260518T092015
DTSTART;TZID=America/Detroit:20260605T130000
DTEND;TZID=America/Detroit:20260605T134500
SUMMARY:Exhibition:Sky Tonight
DESCRIPTION:A live presentation on what to find in the sky tonight and for the coming few weeks. This presentation includes how to find the cardinal directions with the North Star\, current and upcoming constellations\, visible planets\, a few deep sky objects depending on the season\, and other interesting astronomical visualizations. If you want to be able to look up from your own backyard and know what to look for\, this is the show for you.
UID:141325-21903867@events.umich.edu
URL:https://events.umich.edu/event/141325
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Film,Space,Museum,museums,natural history museum,Natural Sciences,Planetarium,Prospective Undergraduate Students,Science,Undergraduate,Children,Astronomy,Family
LOCATION:Museum of Natural History - Planetarium & Dome Theater
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260518T095230
DTSTART;TZID=America/Detroit:20260605T140000
DTEND;TZID=America/Detroit:20260605T144500
SUMMARY:Film Screening:T.REX
DESCRIPTION:With stunning CGI visuals and the latest research from leading paleontologists\, the film offers audiences a fresh perspective on the GOAT (Greatest Of All Tyrants): Tyrannosaurus rex. Anchored by the true story of the young fossil hunters who made the discovery of a lifetime when they spotted a large fossilized leg bone on a walk on public lands in North Dakota\, T. REX intercuts the remarkable fossil dig\, with cutting edge computer graphics that bring the iconic T. rex to life—from hatchling to hulking adult. Narrated by Jurassic Park actor Sam Neill\, T. REX explores the newest science that has helped reinvent our understanding of the iconic predator.
UID:136347-21903895@events.umich.edu
URL:https://events.umich.edu/event/136347
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Planetarium,natural history museum,Museum,Film
LOCATION:Museum of Natural History - Planetarium & Dome Theater
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260518T092015
DTSTART;TZID=America/Detroit:20260605T150000
DTEND;TZID=America/Detroit:20260605T154500
SUMMARY:Exhibition:Sky Tonight
DESCRIPTION:A live presentation on what to find in the sky tonight and for the coming few weeks. This presentation includes how to find the cardinal directions with the North Star\, current and upcoming constellations\, visible planets\, a few deep sky objects depending on the season\, and other interesting astronomical visualizations. If you want to be able to look up from your own backyard and know what to look for\, this is the show for you.
UID:141325-21903871@events.umich.edu
URL:https://events.umich.edu/event/141325
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Film,Space,Museum,museums,natural history museum,Natural Sciences,Planetarium,Prospective Undergraduate Students,Science,Undergraduate,Children,Astronomy,Family
LOCATION:Museum of Natural History - Planetarium & Dome Theater
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260511T164507
DTSTART;TZID=America/Detroit:20260605T180000
DTEND;TZID=America/Detroit:20260605T193000
SUMMARY:Tours:Walking Tour: Creating Michigan: Key Moments in U-M’s Early History
DESCRIPTION:Explore the first 70 years of U-M history\, from the University’s Native American land accession and its origins in Detroit in 1817 to its move to Ann Arbor and emergence as a research university after 1837. We’ll traverse the original 40-acre campus\, learning about the professors\, presidents\, and students who walked the Diag nearly two centuries ago. \n\nGuided walking tour led by student docents. Duration: 1.5 hours\; 0.6 miles.\n\nMeet at the steps of Angell Hall facing State Street. \n\nTour will take place in rain or snow\, but will be cancelled for severe weather (registrants will be notified via email).\n\nRegistration required: https://lp.constantcontactpages.com/ev/reg/2qsese6
UID:148228-21903351@events.umich.edu
URL:https://events.umich.edu/event/148228
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:history,tour,U-m History,university of michigan history,university history
LOCATION:Angell Hall
CONTACT:
END:VEVENT
END:VCALENDAR