Tentative schedule

Workshop took place on July 1st (second day of workshops) in FRN.

Video recording of the workshop


9:00-10:00 Causal reasoning and Learning Systems.
Leon Bottou, Jonas Peters, D. Max Chickering, Patrice Simard
Due to a sudden personal reason Leon cannot attend to ICML this
year. The talk will be given by Elon Portugaly.
10:00-10:30 On Bayesian Bandits Algorithms
Émilie Kaufmann
10:30-11:00 Coffee break
11:00-12:00 Two basic problems in finite stochastic optimization
Sebastien Bubeck
12:00-12:15 Dynamic Pricing with Limited Supply
Moshe Babaioff,Shaddin Dughmi, Robert Kleinberg, Aleksandrs Slivkins
download paper
12:15-12:30 Learning Hurdles for Sleeping Experts
Varun Kanade, Thomas Steinke
 download paper
12:30-12:45  Contextual Bandits: Approximated Linear Bayes for Large Contexts
Jose Antonio Martin H
download paper
12:45-14:00 Lunch
14:00-15:00 The knowledge gradient for optimal learning
Warren B. Powell
15:00-15:10 Introduction to the Exploration & Exploitation Challenge
Jérémie Mary
15:10-15:25 Second team of the Phase 1 presentation
Regulating Greed over Time for Yahoo! Front Page News Article

Cynthia Rudin,  Virot Ta Chiraphadhanakul, Edward Su (MIT)
15:25-15:45 Winner of phase 1 presentation
Upper Confidence Bound with Time Information on News Article

Ku-Chun Chou, Hsuan-Tien Lin (National Taiwan University)
15:45-16:00 Coffee break
16:00-16:10 Annoucement of winners of Phase 2
16:10-17:10 Open discussion on future of exploration & exploitation


You can find the last year proceedings (2011 edition) on  JMLR Workshop series