BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Eurandom - ECPv4.8.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Eurandom
X-ORIGINAL-URL:https://www.eurandom.tue.nl
X-WR-CALDESC:Events for Eurandom
BEGIN:VEVENT
DTSTART;VALUE=DATE:20190319
DTEND;VALUE=DATE:20190323
DTSTAMP:20190325T042100
CREATED:20181112T134508Z
LAST-MODIFIED:20190318T121451Z
UID:2339-1552953600-1553299199@www.eurandom.tue.nl
SUMMARY:YES X : "Understanding Deep Learning: Generalization\, Approximation and Optimization"
DESCRIPTION:Summary\nDuring the last decade\, deep learning has drawn increasing attention both in machine learning and statistics because of its superb empirical performance in various fields of application\, including speech and image recognition\, natural language processing\, social network filtering\, bioinformatics\, drug design and board games (e.g. Alpha go\, Alpha zero). This raises important and fundamental questions on why these methods are so successful\, and to what extent they can be applied to a wide range of problems. \nAlthough theoretical results from the 1980s and 1990s already describe the statistical behavior of small neural networks if we assume their parameters can be optimized exactly\, this situation is far from what happens in practice. Instead\, two crucial features of modern applications are that the number of parameters is much larger than the sample size\, and that non-convexity fundamentally prevents optimization methods from finding the globally optimal parameters. In fact\, it has become clear that the statistical properties of deep learning are inextricably intertwined with how their parameters are being optimized. To explain the behavior of modern deep learning it is therefore necessary to understand the subtle interplay between generalization\, approximation and optimization. Developing such an understanding is particularly important if deep learning is to play a role in more sensitive application areas such as medical practice\, self-driving cars\, air-traffic control\, and so on. \nThe aim of the workshop is to give a balanced representation of the most recent advances on these topics\, from theory to applications\, and spanning both statistics\, optimization and machine learning topics. The workshop targets primarily (but not exclusively) young researchers\, in particular PhD students\, postdocs and junior early stage researchers. The workshop will take place over 4 days and consists of tutorial courses and invited talks given by world experts in the field. The tutorial courses will each consist of roughly of 3 hours of lectures and the invited talks will be 1 hour. Furthermore\, some of the junior participants will be given the opportunity to present their current work during the workshop by giving a short (30 minutes) oral presentation and possibly poster presentations (depending on the number of submissions). \nOrganizers\n\n\n\nPaulo de Andrade Serra\nTU Eindhoven\n\n\nRui Pires da Silva Castro\nTU Eindhoven\n\n\nTim van Erven\nLeiden University\n\n\nBotond Szabo\nLeiden University\n\n\n\nTutorial Speakers\n\n\n\nPeter Bartlett\nUniversity of California - Berkeley\n\n\nJohannes Schmidt-Hieber\nUniversity of Twente\n\n\nNathan Srebro\nToyota Technological Institute at Chicago and University of Chicago\n\n\n\nInvited Speakers\n\n\n\nMax Welling\nUniversity of Amsterdam\n\n\nTaco Cohen\nUniversity of Amsterdam\n\n\nJulien Mairal\nINRIA - Grenoble\n\n\nSander Bohté\nCWI\n\n\n\nProgramme\nThe workshop schedule is available here: YES2019_schedule.pdf \nAbstracts\nAbstracts for the tutorial\, invited and contributed talks can be found here: YES2019_abstracts.pdf \nRegistration\nWe are at full capacity for this workshop. The registration is therefore closed! \nPractical Information\nLink to information page \nSponsors and Financial Support\n \n \n
URL:https://www.eurandom.tue.nl/event/yes-x-deep-learning-foundations/
LOCATION:Eurandom\, Metaforum\, Eindhoven\, Netherlands
CATEGORIES:YES
END:VEVENT
END:VCALENDAR