Workshops

Summer 2019

Emerging Challenges in Deep Learning

Aug 5, 2019 to Aug 8, 2019

Return to event »

Monday, August 5th, 2019
9:00 am–9:20 am		Coffee and Check-In
9:20 am–9:30 am		Opening Remarks
9:30 am–10:15 am		Knowledge is embedded in language neural networks but can they reason? Chris Manning (Stanford University)
10:15 am–11:00 am		Machine Learning-based Design of Proteins and Small Molecules Jennifer Listgarten (UC Berkeley)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Efficient Deep Learning with Humans in the Loop Zachary Lipton (Carnegie Mellon University)
12:15 pm–2:15 pm		Lunch
2:15 pm–3:00 pm		Aligning ML objectives with human values Paul Christiano (Open AI)
3:00 pm–3:45 pm		Is Deeper Better Only When Shallow Is Good? Shai Shalev-Shwartz (The Hebrew University of Jerusalem)
3:45 pm–4:15 pm		Break
4:15 pm–5:00 pm		Flexible Neural Networks and the Frontiers of Meta-Learning Chelsea Finn (Stanford University)
5:00 pm–6:00 pm		Reception

Tuesday, August 6th, 2019
9:00 am–9:30 am		Coffee and Check-In
9:30 am–10:15 am		On the Hardness of Reinforcement Learning With Value-function Approximation Nan Jiang (University of Illinois Urbana-Champaign)
10:15 am–11:00 am		Reinforcement Learning in Feature Space: Complexity and Regret Mengdi Wang (Princeton University)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes Alekh Agarwal (Microsoft Research Redmond)
12:15 pm–2:15 pm		Lunch
2:15 pm–3:00 pm		Off-policy Policy Optimization Dale Schuurmans (Google Brain & University of Alberta)
3:00 pm–3:45 pm		Reinforcement Learning in Recommender Systems: Some Challenges Craig Boutilier (Google and University of Toronto)
3:45 pm–4:15 pm		Break
4:15 pm–5:00 pm		Panel Panelists: 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) Moderators: Po-Ling Loh (University of Wisconsin, Madison), Matus Telgarsky (University of Illinois, Urbana-Champaign)

Wednesday, August 7th, 2019
9:00 am–9:30 am		Coffee and Check-In
9:30 am–10:15 am		Reinforcement Learning via an Optimization Lens Lihong Li (Google Brain)
10:15 am–11:00 am		Towards Verified Deep Learning Sanjit Seshia (UC Berkeley)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Integrating Constraints into Deep Learning Architectures with Structured Layers Zico Kolter (CMU Bosch)
12:15 pm–2:15 pm		Lunch
2:15 pm–3:00 pm		The Measure and Mismeasure of Fairness Sharad Goel (Stanford University)
3:00 pm–3:45 pm		Procurement as Policy: Administrative Process For Machine Learning Deirdre Mulligan (UC Berkeley)
3:45 pm–4:15 pm		Break
4:15 pm–5:00 pm		Panel on Ethics Panelists: Sharad Goel (Stanford University), Deirdre Mulligan (UC Berkeley), Emily Witt (Salesforce), Alice Xiang (Partnership on AI) Moderators: Deirdre Mulligan (UC Berkeley), Matus Telgarsky (University of Illinois, Urbana-Champaign)

Thursday, August 8th, 2019
10:15 am–10:45 am		Coffee and Check-In
10:45 am–11:30 am		Inherent Trade-offs with the Local Explanations Paradigm Julius Adebayo (MIT)
11:30 am–12:15 pm		How to Fail Interpretability Research Been Kim (Google Brain)
12:15 pm–2:15 pm		Lunch
2:15 pm–3:00 pm		Better Learning from the Past: Counterfactual / Batch RL Emma Brunskill (Stanford University)
3:00 pm–3:45 pm		Designing Robust Learners Jacob Steinhardt (Stanford University)