BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: The Non-Stochastic Control Problem
DTSTART:20191122T161500
DTEND:20191122T171500
DTSTAMP:20260407T050936Z
UID:066664cd680d880190ce575eaab7a3915b283e7819b77e432a248fbf
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Elad Hazan - Princeton University\nVideo of his talk\n\nAb
 stract:\nLinear dynamical systems are a continuous subclass of reinforceme
 nt learning models that are widely used in robotics\, finance\, engineerin
 g\, and meteorology.\nClassical control\, since the work of Kalman\, has f
 ocused on dynamics with Gaussian i.i.d. noise\, quadratic loss functions a
 nd\, in terms of provably efficient algorithms\, known systems and observe
 d state.\n\nWe'll discuss how to apply new machine learning methods to con
 trol which relax all of the above: efficient control with adversarial nois
 e\, general loss functions\, unknown systems\, and partial observation.\n\
 nBio:\nElad Hazan is a professor of computer science at Princeton Universi
 ty. His research focuses on the design and analysis of algorithms for basi
 c problems in machine learning and optimization. Amongst his contributions
  are the co-development of the AdaGrad optimization algorithm\, and the fi
 rst sublinear-time algorithms for convex optimization. He is the recipient
  of the Bell Labs prize\, (twice) the IBM Goldberg best paper award in 201
 2 and 2008\, a European Research Council grant\, a Marie Curie fellowship 
 and Google Research Award (twice). He served on the steering committee of 
 the Association for Computational Learning and has been program chair for 
 COLT 2015. In 2017 he co-founded In8 inc. focusing on efficient optimizati
 on and control\, acquired by Google in 2018. He is the co-founder and dire
 ctor of Google AI Princeton.\n\nResearch interests: Control and Reinforcem
 ent Learning\, Optimization for Machine Learning\, Online Convex Optimizat
 ion. More details and links to the relevant papers are in this page.\n\nLi
 nk to full CV \n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR