BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260522T150119Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181113T083000
DTEND;TZID=America/Chicago:20181113T170000
UID:submissions.supercomputing.org_SC18_sess322_post130@linklings.com
SUMMARY:Cross-Layer Group Regularization for Deep Neural Network Pruning
DESCRIPTION:Shuang Gao and Xin Liu (Nvidia Corporation)\n\nImproving weigh
 ts sparsity is a common strategy for deep neural network pruning. Most exi
 sting methods use regularizations that only consider structural sparsity w
 ithin an individual layer. In this paper, we propose a cross-layer group r
 egularization taking into account the statistics from multiple layers. For
  residual networks, we use this approach to align kernel sparsity across l
 ayers that are tied to each other through element-wise operations: the ith
  kernel of these layers are put into one regularization group, they either
  stay or be removed simultaneously during pruning. In this way, the comput
 ational and parameter storage cost could be significantly reduced. Experim
 ental results show that this method does not only  improve weights sparsit
 y but also align kernel weights sparsity across related layers. Our method
  is able to prune ResNet up to 90.4% of parameters and improve runtime by 
 1.5x speedup, without loss of accuracy.\n\nRegistration Category: Tech Pro
 gram Reg Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR