Programme > Keynote speakers

Emilie Kaufmann CNRS/ INRIA Lille	Christian Theobalt MaxPlanck Institut	Rachid Guerraoui EPFL/ Chaire du collège de France	Diane Larlus Naver Labs Europe	Arthur Gretton University College of London

WENESDAY

Christian Theobalt (MaxPlanck Institut)

Title: Capturing the Real World in Motion: New ways to unite graphics, vision and machine learning

Abstract:

Bio: Christian Theobalt is a Professor of Computer Science and the head of the research group "Graphics, Vision, & Video" at the Max-Planck-Institute (MPI) for Informatics, Saarbrücken, Germany. He is also a Professor of Computer Science at Saarland University, Germany. From 2007 until 2009 he was a Visiting Assistant Professor in the Department of Computer Science at Stanford University.He received his MSc degree in Artificial Intelligence from the University of Edinburgh, his Diplom (MS) degree in Computer Science from Saarland University, and his PhD (Dr.-Ing.) from Saarland University and Max-Planck-Institute for Informatics.In his research he looks at algorithmic problems that lie at the intersection of Computer Graphics, Computer Vision and machine learning, such as: static and dynamic 3D scene reconstruction, marker-less motion and performance capture, virtual and augmented reality, computer animation, appearance and reflectance modelling, intrinsic video and inverse rendering, machine learning for graphics and vision, new sensors for 3D acquisition, advanced video processing, as well as image- and physically-based rendering. He is also interested in using reconstruction techniques for human computer interaction.For his work, he received several awards, including the Otto Hahn Medal of the Max-Planck Society in 2007, the EUROGRAPHICS Young Researcher Award in 2009, the German Pattern Recognition Award 2012, and the Karl Heinz Beckurts Award in 2017. He received two ERC grants, one of the most prestigious and competitive individual research grants in Europe: An ERC Starting Grant in 2013 and an ERC Consolidator Grant in 2017. He is a Fellow of ELLIS, the European lab for Learning & Intelligent Systems. In 2015, he was elected as one of the top 40 innovation leaders under 40 in Germany by the business magazine Capital. Christian Theobalt is also a co-founder of an award-winning spin-off company from his group - www.thecaptury.com - that is commercializing one of the most advanced solutions for marker-less motion and performance capture.

Rachid Guerraoui (EPFL/ Chaire du collège de France)

Title:

Abstract:

THURSDAY

Diane Larlus (Naver Labs Europe)

Title:

Abstract:

Arthur Gretton (University College of London)

Title:

Abstract:

FRIDAY

Emilie Kaufmann (CNRS/ INRIA Lille)

Title: Thompson Sampling for Reinforcement Learning and Beyond

Abstract: Multi-armed bandits are powerful tools to model many sequential decision making problems. This talk will revolve around Thompson Sampling, a Bayesian strategy first proposed in 1933 that can solve the most common bandit problem in which an agent repeatedly chooses actions (called arms) and receives rewards that are to be maximized. This algorithm was not so long ago shown to be optimal for this problem, and is now also considered for more sophisticated reinforcement learning tasks. However, not all bandits problems are reinforcement learning problems : the agent may also perform active identification, that is seek an answer to some question about the probability distributions underlying the arms (e.g. find the arm that yields the largest expected payoff), without the incentive to maximize rewards in the process. Vanilla Thompson Sampling cannot be used in this setting as it would explore the most rewarding arm too much. In the second part of this talk, we will discuss some adaptations of Thompson Sampling for active identification in multi-armed bandit models.