CALL FOR PAPERS
NeurIPS 2019 Workshop: Safety and Robustness in Decision-making Vancouver, Friday December 13, 2019 https://sites.google.com/view/neurips19-safe-robust-workshop IMPORTANT DATES Paper Submission Deadline: September 22, 2019 Notification of Acceptance: September 30, 2019 Workshop: Friday December 13, 2019 WORKSHOP OVERVIEW Interacting with increasingly sophisticated decision-making systems is becoming more and more a part of our daily life. This creates an immense responsibility for designers of these systems to build them in a way to guarantee safe interaction with their users and good performance, in the presence of noise and changes in the environment, and/or of model misspecification and uncertainty. Any progress in this area will be a huge step forward in using decision-making algorithms in emerging high stakes applications, such as autonomous driving, robotics, power systems, health care, recommendation systems, and finance. This workshop aims to bring together researchers from academia and industry in order to discuss main challenges, describe recent advances, and highlight future research directions pertaining to develop safe and robust decision-making systems. We aim to highlight new and emerging theoretical and applied research opportunities for the community that arise from the evolving needs for decision-making systems and algorithms that guarantee safe interaction and good performance under a wide range of uncertainties in the environment. The research challenges we are interested in addressing in this workshop include (but not limited to): - Counterfactual reasoning and off-policy evaluation. - How to learn a policy that either has certain performance (safety w.r.t. a baseline) or avoids certain undesirable situations (safety w.r.t. undesirable situations) in the presence of model uncertainty? - How to (safely) explore the environment and update the model in order to maximize either the model improvement or the performance of the policy learned from the new (updated) model? - How to measure robustness? Robustness is becoming an overused term with too many different meanings - How to balance robustness with performance? Existing robust solutions are often optimize for the worst-case scenario, and thus, are overly conservative (give up too much on the performance). - Better understanding the relation between risk and robustness. SUBMISSION INSTRUCTIONS Papers submitted to the workshop should be between 4 to 8 pages long, excluding references and appendix, and in NeurIPS 2019 format (NOT ANONYMIZED). Accepted papers will be presented as posters or contributed oral presentations. Submissions should be sent as a pdf file by email to safe.robust.neurips19.works...@gmail.com INVITED SPEAKERS Finale Doshi-Velez (Harvard University) Dimitar Filev (Ford Motor Company) Thorsten Joachims (Cornell University) Nathan Kallus (Cornell University) Daniel Kuhn (EPFL) Scott Niekum (University of Texas at Austin) Marco Pavone (Stanford University) Andy Sun (Georgia Tech) Aviv Tamar (Technion) ORGANIZERS Yinlam Chow (Google Research) Mohammad Ghavamzadeh (Facebook AI Research) Shie Mannor (Technion) Marek Petrik (University of New Hampshire) Yisong Yue (Caltech)
_______________________________________________ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
