BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 21.0.11
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
END:STANDARD
END:VTIMEZONE				
BEGIN:VEVENT
DTSTAMP:20240627T112257
UID:d71c767c-3466-11ef-9c63-000e0c3db68b
SUMMARY:Talk of Dr. Claire Vernade
DESCRIPTION:Dr. Claire Vernade\nUniversity of Tübingen\nTübingen, Germany\n\n  \nTuesday 2024-07-02 4 p.m.\nIST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract\nDiscovery in Science is a complex process that involves exploration and planning, as well as\nhypothesis testing. In this talk, I will discuss why I believe that Reinforcement Learning can be\nan important ingredient in Machine Learning for Science. I will present 2 recent works I have\nbeen working on with my group: \n\nA Pontryagin's perspective on Open-Loop Reinforcement Learning:   \nhttps://arxiv.org/abs/2405.18100 (w/ Onno Eberhard\nand Michael Mühlebach)\nPrior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured\nBandits: \nhttps://arxiv.org/abs/2402.05878 (with Nicolas\nNguyen, Imad Aouali, Andras György)\n\nThe talk will start with a gentle introduction to Reinforcement Learning Theory.  \nBiographical Information\nClaire is a Group Leader at the University of Tuebingen, in the  \nCluster of Excellence Machine Learning for\nScience(*). She was awarded an  \nEmmy Noether\naward under the AI Initiative call in 2022. \nHer research is on sequential decision making. It mostly spans bandit problems, and\ntheoretical Reinforcement Learning, but her research interests extend to Learning Theory and\nprincipled learning algorithms. Her goal is to make Machine Learning a continual process whose\ndynamical aspects are understood and controlled. \nBetween November 2018 and December 2022, she was a Research Scientist at DeepMind in London\nUK in the Foundations team lead by  \nProf. Csaba Szepesvari. She did a post-doc in\n2018 with  \nProf. Alexandra\nCarpentier at the University of Magdeburg in Germany while working part-time as\nan Applied Scientist at Amazon in Berlin. She received her PhD from Telecom ParisTech in\nOctober 2017, under the guidance of  \nProf. Olivier Cappé. \nI am co-leading the  \nWomen in Learning Theory initiative as well as the new\ngroup of  \nTübingen Women in Machine Learning, please reach out\nif you have questions or if you'd like to help.\n\n\n\n 
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20240702
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/events/Talk-of-Dr.-Claire-Vernade/
END:VEVENT
END:VCALENDAR