BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.13.0//EN
X-ORIGINAL-URL:https://dcn.nat.fau.eu/
X-WR-CALNAME:
X-WR-CALDESC:FAU DCN-AvH. Chair for Dynamics, Control, Machine Learning and Numerics -Alexander von Humboldt Professorship
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-fdf2aade29d18910051a6c76ae661860@dcn.nat.fau.eu
DTSTART:20210505T083000Z
DTEND:20210505T093000Z
DTSTAMP:20211020T063800Z
CREATED:20211020
LAST-MODIFIED:20220117
PRIORITY:5
SEQUENCE:0
TRANSP:OPAQUE
SUMMARY:Variational problems on L-infinity and continuum limits on graphs
DESCRIPTION:Speaker: Dr. Leon Bungert\nAffiliation: FAU Erlangen-Nürnberg, Germany\nOrganized by: FAU CAA-AvH, Chair in Applied Analysis – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany)\nZoom meeting link\nMeeting ID: 623 9301 9630 | PIN code: 158499\nAbstract. Modern machine learning techniques and in particular Deep Learning have surpassed classical methods both in terms of efficiency and accuracy. On the other hand, many (semi)supervised learning methods are inherently instable with respect to noise or so-called adversarial examples which hinders their usage in safety critical applications. A potential remedy for this drawback is to design Lipschitz continuous, and hence stable, inference models. In this talk I will first speak about a graph-based semi-supervised learning approach called Lipschitz learning and study its continuum limit as the number of data points tends to infinity. Using Gamma-convergence one can prove that minimizers converge to solutions of a variational problem in L-infinity. Then I will present a novel regularization algorithm for neural networks called CLIP, which penalizes large Lipschitz constants of a neural network during training by keeping track of the set of unstable points.\n
URL:https://dcn.nat.fau.eu/events/variational-problems-on-l-infinity-and-continuum-limits-on-graphs/
CATEGORIES:FAU CAA Seminar
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/FAUDDS-CAASeminars-05may2021.png
END:VEVENT
END:VCALENDAR