BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Mathematics - ECPv5.7.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Mathematics
X-ORIGINAL-URL:https://math.sciences.ncsu.edu
X-WR-CALDESC:Events for Department of Mathematics
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20201204T124500
DTEND;TZID=America/New_York:20201204T131500
DTSTAMP:20210613T160221
CREATED:20201201T144703Z
LAST-MODIFIED:20201201T144909Z
UID:18508-1607085900-1607087700@math.sciences.ncsu.edu
SUMMARY:Weilin Li\, Courant Institute\, Generalization error of minimum weighted norm and kernel interpolation
DESCRIPTION:A central question in machine learning theory is whether an algorithm enjoys good generalization\, which is the ability to correctly predict new examples from prior observations. While classical wisdom advocates for methods with fewer parameters than data points in order to avoid overfitting\, modern machine learning algorithms are severely over-parameterized and perfectly fit training data. In this talk\, we study the generalization error of a simple and ubiquitous over-parameterized algorithm: we select a function belonging to a function space of dimension p that interpolates n prescribed data points by minimizing a chosen weighted norm\, where p >> n. Under natural and general conditions\, we prove that both the interpolants and their generalization errors converge as the number of parameters grow\, and the limiting interpolant belongs to a reproducing kernel Hilbert space. This rigorously establishes an implicit bias of minimum weighted norm interpolation and explains why norm minimization may benefit from over-parameterization. As special cases of this theory\, we study interpolation by trigonometric polynomials and spherical harmonics. Our approach is from a deterministic and approximation theory viewpoint\, as opposed to a statistical or random matrix one.
URL:https://math.sciences.ncsu.edu/event/weilin-li-courant-institute-generalization-error-of-minimum-weighted-norm-and-kernel-interpolation/
LOCATION:Zoom
CATEGORIES:Special Seminar
END:VEVENT
END:VCALENDAR