BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.1//EN
X-ORIGINAL-URL:https://matematica.unipv.it/
X-WR-CALNAME:Dipartimento di Matematica UNIPV
X-WR-CALDESC:
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
DTSTART;TZID=Europe/Rome:20220628T150000
DTEND;TZID=Europe/Rome:20220628T160000
DTSTAMP:20220519T112300
UID:MEC-8d80b953e6dab669d98c905f7527fedd@matematica.unipv.it
CREATED:20220519
LAST-MODIFIED:20220519
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:Ensemble optimal control: ResNets, diffeomorphisms approximation and Normalizing Flows
DESCRIPTION:Ensemble optimal control: ResNets, diffeomorphisms approximation and Normalizing Flows\nAlessandro Scagliotti (SISSA Trieste)\nAbstract: In the last years it was observed that Residual Neural Networks (ResNets) can be interpreted as discretizations of control systems, bridging ResNets (and, more generally, Deep Learning) with Control Theory. In the first part of this seminar we formulate the task of a data-driven reconstruction of a diffeomorphism as an ensemble optimal control problem. In the second part we adapt this machinery to address the problem of Normalizing Flows: after observing some samplings of an unknown probability measure, we want to (approximately) construct a transport map that brings a “simple” distribution (e.g., a Gaussian) onto the unknown target distribution. In both the problems we use tools from $\Gamma$-convergence to study the limiting case when the size of the data-set tends to infinity.\n
URL:https://matematica.unipv.it/events/ensemble-optimal-control-resnets-diffeomorphisms-approximation-and-normalizing-flows/
ORGANIZER;CN=Alessandro Scagliotti (SISSA Trieste):MAILTO:
CATEGORIES:Seminari di matematica applicata
LOCATION:Aula Beltrami
END:VEVENT
END:VCALENDAR