BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Robust and Practical Bayesian Optimization and Beyond
DTSTART:20190128T110000
DTEND:20190128T120000
DTSTAMP:20260406T184128Z
UID:d4f4a31ae0cd913cba8e65ea0efc3e8e8ccd5ba85545da5c44245dd3
CATEGORIES:Conferences - Seminars
DESCRIPTION:Volkan Cevher (EPFL)\nThe central task in many interactive mac
 hine learning systems can be formalized as the sequential optimization of 
 a black-box function. Bayesian optimization (BO) is a powerful model-based
  framework for adaptive experimentation\, where the primary goal is the op
 timization of the black-box function via sequentially chosen decisions. In
  many real-world tasks\, it is essential for the decisions to be robust ag
 ainst\, e.g.\, adversarial failures and perturbations\, dynamic and time-v
 arying phenomena\, a mismatch between simulations and reality\, etc. Under
  such requirements\, the standard methods and BO algorithms become inadequ
 ate. In this talk\, we discuss algorithms with provable regret guarantees 
 that can enhance robust and adaptive decision making in BO and related pro
 blems. We also consider associated robust submodular and non-submodular op
 timization problems\, and present practical and efficient algorithms with 
 improved robustness and constant factor approximation guarantees. Finally\
 , we demonstrate the robust performance of our algorithms in numerous real
 -world applications (e.g.\, environmental monitoring and recommender syste
 ms) and tasks (e.g.\, robot pushing and feature selection). \n\nKey words
 : Bayesian optimization\, Gaussian process\, Submodularity\, Robust optim
 ization\, Regret bounds\, Level-set estimation\, Non-submodular optimizati
 on\n\nAbout the speaker — Volkan Cevher received the B.Sc. (valedicto
 rian) in electrical engineering from Bilkent University in Ankara\, Turkey
 \, in 1999 and the Ph.D. in electrical and computer engineering from the G
 eorgia Institute of Technology in Atlanta\, GA in 2005. He was a Research 
 Scientist with the University of Maryland\, College Park from 2006-2007 an
 d also with Rice University in Houston\, TX\, from 2008-2009. Currently\, 
 he is an Associate Professor at the Swiss Federal Institute of Technology 
 Lausanne and a Faculty Fellow in the Electrical and Computer Engineering D
 epartment at Rice University. His research interests include signal proces
 sing theory\, machine learning\, convex optimization\, and information the
 ory. Dr. Cevher was the recipient of the IEEE Signal Processing Society 
 Best Paper Award in 2016\, a Best Paper Award at CAMSAP in 2015\, a Best P
 aper Award at SPARS in 2009\, and an ERC CG in 2016 as well as an ERC StG 
 in 2011.
LOCATION:CO 121 https://plan.epfl.ch/?room=CO121
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR