BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000602Z
LOCATION:DEF Concourse
DTSTART;TZID=America/Denver:20231114T100000
DTEND;TZID=America/Denver:20231114T170000
UID:submissions.supercomputing.org_SC23_sess291_rpost120@linklings.com
SUMMARY:Preserving Data Locality in Multidimensional Variational Quantum C
 lassification
DESCRIPTION:Mingyoung Jeng, Alvir Nobel, Vinayak Jha, David Levy, Dylan Kn
 eidel, Manu Chaudhary, Ishraq Islam, and Esam El-Araby (University of Kans
 as)\n\nIn classical machine learning, the convolution operation is leverag
 ed in the eponymous class of convolutional neural networks (CNNs) capturin
 g the spatial and/or temporal locality of multidimensional input features.
  Preserving data locality allows CNN models to reduce the number of traini
 ng parameters, and hence their training time, while achieving high classif
 ication accuracy. However, contemporary methods of quantum machine learnin
 g do not possess effective methods for exploiting data locality, due to th
 e lack of a generalized and parameterizable implementation of quantum conv
 olution. In this work, we propose variational quantum classification techn
 iques that leverage a novel multidimensional quantum convolution operation
  with arbitrary filtering and unity stride. We provide the quantum circuit
 s for our techniques alongside corresponding theoretical analysis. We also
  experimentally demonstrate the advantage of our method in comparison with
  existing quantum and classical techniques for image classification in sta
 ple multidimensional datasets using state-of-the-art quantum simulations.\
 n\nTag: Artificial Intelligence/Machine Learning, Architecture and Network
 s, Heterogeneous Computing, I/O and File Systems, Performance Measurement,
  Modeling, and Tools, Post-Moore Computing, Programming Frameworks and Sys
 tem Software, Quantum Computing\n\nRegistration Category: Tech Program Reg
  Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR