BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-291925ddbc6e2d194d0c22d268e0f865@cmc.deusto.eus
DTSTART:20201109T070000Z
DTEND:20201113T170000Z
DTSTAMP:20200513T164100Z
CREATED:20200513
LAST-MODIFIED:20200918
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:Workshop: Optimal Control, Optimal Transport and Data Science
DESCRIPTION:IMA – Institute for Mathematics and its Applications with Carnegie Mellon University and IBM organizes the workshop: Optimal Control, Optimal Transport and Data Science\nOptimal control and optimal transportation have begun to play an important role in data science. Many techniques of machine learning, including deep learning, high-dimensional statistical learning, transfer learning, anomaly detection, and prediction from expert advice, rely on optimal transport and optimal control to model tasks, compute solutions, and provide theoretical analysis of the algorithms. Optimal transport has been successfully used as a loss function in both theory and practice to provide robust learning approaches. Furthermore, Wasserstein Generative Adversarial Networks (WGAN) have achieved state-of-the-art results for generative learning problems. In deep learning, optimal control of ordinary differential equations has been connected recently with the stability of ResNet neural networks. Reformulation training as an optimal control problem has led to new training algorithms based on Pontryagin’s maximum principle. Furthermore, minimax optimal strategies for minimizing regret have been connected to continuum Hamilton-Jacobi-Isaacs partial differential equations (PDEs). Despite this flurry of work and recent success, many theoretical and computational challenges remain, such as fast computation of optimal transportation distances and maps.\nApply to the IMA workshop\n
URL:https://cmc.deusto.eus/events-calendar/workshop-optimal-control-optimal-transport-and-data-science/
CATEGORIES:Events Calendar,Events Calendar Past
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/2020/05/logo-IMA.png
END:VEVENT
END:VCALENDAR
