Schedule
9.00 - Introduction
9.10 - Invited talk: Personalization via Deep, Meaningful, and Long-Term Learning, Tony Jebara (Netflix)
9.40 - On the Value of Bandit Feedback for Offline Recommender System Evaluation (slides) // Olivier Jeunen (University of Antwerp); David J Rohde (Criteo); Flavian Vasile (Criteo)
10.05 - Sudden Death: A New Way to Compare Recommendation Diversification (slides) // Derek Bridge (University College Cork); Mesut Kaya (University College Cork); Pablo Castells (Universidad Autónoma de Madrid)
10.30 - Coffee Break / Posters
11.20 - Invited talk: Reinforcement Learning for Recommender Systems: Some Challenges, Craig Boutilier (Google)
11.40 - Marginal Posterior Sampling for Slate Bandits // Maria Dimakopoulou (Netflix); Nikos Vlassis (Netflix); Yves Raimond (Netflix); Tony Jebara (Netflix)
12.00 - Surprise Announcement!
12.10 - Lunch break
14.00 - Invited talk: Engagement, metrics and recommenders (slides) // Mounia Lalmas (Spotify)
14.30 - Learning from Bandit Feedback: An Overview of the State-of-the-art (slides) // Olivier Jeunen (University of Antwerp); David J Rohde (Criteo); Flavian Vasile (Criteo); Alexandre Gilotte (Criteo); Martin Bompaire (Criteo)
14.50 - Generalizable Recommendation to a Target Population by Leveraging Randomized and Observational Studies (slides) // Lili Wu (North Carolina State University); Shu Yang (North Carolina State University)
15.15 - Coffee break / Posters
16.00 - Invited talk: Optimizing for Causal Outcomes in Online Advertising // Damien Lefortier (Facebook)
16.20 - Recap: Designing a more Efficient Estimator for Off-policy Evaluation in Bandits with Large Action Spaces (slides) // Ajinkya More (Netflix), Linas Baltrunas (Netflix), Nikos Vlassis (Netflix), Justin Basilico (Netflix)
16.40 - Sequence-aware Reinforcement Learning over Knowledge Graphs // Rishabh Mehrotra (Spotify); Ashish Gupta (WalmartLabs)
17.00 - Panel / fireside chat with invited speakers
17.20 - End of workshop