BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IFDS - ECPv6.0.1.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:IFDS
X-ORIGINAL-URL:https://ifds.info
X-WR-CALDESC:Events for IFDS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20220313T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20221106T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20220204T123000
DTEND;TZID=America/Los_Angeles:20220204T133000
DTSTAMP:20260515T233614
CREATED:20220325T195559Z
LAST-MODIFIED:20220325T195650Z
UID:1915-1643977800-1643981400@ifds.info
SUMMARY:IFDS Monthly All-Hands: Rebecca Willett
DESCRIPTION:Speaker: Prof. Rebecca Willett\, Statistics and CS\, University of Chicago   \nTitle: The Role of Linear Layers in Nonlinear Interpolating Networks   \nAbstract: In this discussion\, we will explore the implicit bias of overparameterized neural networks of depth greater than two layers. Our framework considers a family of networks of varying depth that all have the same capacity but different implicitly defined representation costs. The representation cost of a function induced by a neural network architecture is the minimum sum of squared weights needed for the network to represent the function; it reflects the function space bias associated with the architecture. Our results show that adding linear layers to a ReLU network yields a representation cost that reflects a complex interplay between the alignment and sparsity of ReLU units. Specifically\, using a neural network to fit training data with minimum representation cost yields an interpolating function that is constant in directions perpendicular to a low-dimensional subspace on which a parsimonious interpolant exists. This is joint work with Greg Ongie.
URL:https://ifds.info/event/ifds-monthly-all-hands-rebecca-willett/
LOCATION:WI
CATEGORIES:Monthly All-Hands
END:VEVENT
END:VCALENDAR