–
Coffee and Check-In
–
Opening Remarks
–
Knowledge is embedded in language neural networks but can they reason?
Chris Manning (Stanford University)
–
Machine Learning-based Design of Proteins and Small Molecules
Jennifer Listgarten (UC Berkeley)
–
Break
–
Efficient Deep Learning with Humans in the Loop
Zachary Lipton (Carnegie Mellon University)
–
Lunch
–
Aligning ML objectives with human values
Paul Christiano (US AI Safety Institute)
–
Is Deeper Better Only When Shallow Is Good?
Shai Shalev-Shwartz  (The Hebrew University of Jerusalem)
–
Break
–
Flexible Neural Networks and the Frontiers of Meta-Learning
Chelsea Finn (Stanford University)
–
Reception
–
Coffee and Check-In
–
On the Hardness of Reinforcement Learning With Value-function Approximation
Nan Jiang (University of Illinois Urbana-Champaign)
–
Reinforcement Learning in Feature Space: Complexity and Regret
Mengdi Wang (Princeton University)
–
Break
–
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes
Alekh Agarwal (Microsoft Research Redmond)
–
Lunch
–
Off-policy Policy Optimization
Dale Schuurmans (Google Brain & University of Alberta)
–
Reinforcement Learning in Recommender Systems: Some Challenges
Craig Boutilier (Google and University of Toronto)
–
Break
–
Panel
Lihong Li  (Google Brain), Jennifer Listgarten (UC Berkeley), Elchanan Mossel (Massachusetts Institute of Technology), Shai Shalev-Shwartz  (The Hebrew University of Jerusalem), Mengdi Wang (Princeton University), Po-Ling Loh (University of Wisconsin, Madison), Matus Telgarsky (New York University)
–
Coffee and Check-In
–
Reinforcement Learning via an Optimization Lens
Lihong Li (Google Brain)
–
Towards Verified Deep Learning
Sanjit Seshia (UC Berkeley)
–
Break
–
Integrating Constraints into Deep Learning Architectures with Structured Layers
Zico Kolter (CMU Bosch)
–
Lunch
–
The Measure and Mismeasure of Fairness
Sharad Goel (Stanford University)
–
Procurement as Policy: Administrative Process For Machine Learning
Deirdre Mulligan (UC Berkeley)
–
Break
–
Panel on Ethics
Sharad Goel (Stanford University), Deirdre Mulligan (UC Berkeley), Emily Witt (Salesforce), Alice Xiang (Partnership on AI), Deirdre Mulligan (UC Berkeley), Matus Telgarsky (New York University)
–
Coffee and Check-In
–
Inherent Trade-offs with the Local Explanations Paradigm
Julius Adebayo (MIT)
–
How to Fail Interpretability Research
Been Kim (Google Brain)
–
Lunch
–
Better Learning from the Past: Counterfactual / Batch RL
Emma Brunskill (Stanford University)
–
Designing Robust Learners
Jacob Steinhardt (Stanford University)