Emerging Challenges in Deep Learning

Program

Foundations of Deep Learning

Location

Calvin Lab auditorium

Date

Monday, Aug. 5 – Thursday, Aug. 8, 2019

Back to calendar

9 – 9:20 a.m.

Coffee and Check-In

9:20 – 9:30 a.m.

Opening Remarks

9:30 – 10:15 a.m.

Knowledge is embedded in language neural networks but can they reason?

Chris Manning (Stanford University)

10:15 – 11 a.m.

Machine Learning-based Design of Proteins and Small Molecules

Jennifer Listgarten (UC Berkeley)

11 – 11:30 a.m.

Break

11:30 a.m. – 12:15 p.m.

Efficient Deep Learning with Humans in the Loop

Zachary Lipton (Carnegie Mellon University)

12:15 – 2:15 p.m.

Lunch

2:15 – 3 p.m.

Aligning ML objectives with human values

Paul Christiano (US AI Safety Institute)

3 – 3:45 p.m.

Is Deeper Better Only When Shallow Is Good?

Shai Shalev-Shwartz (The Hebrew University of Jerusalem)

3:45 – 4:15 p.m.

Break

4:15 – 5 p.m.

Flexible Neural Networks and the Frontiers of Meta-Learning

Chelsea Finn (Stanford University)

5 – 6 p.m.

Reception

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:15 a.m.

On the Hardness of Reinforcement Learning With Value-function Approximation

Nan Jiang (University of Illinois Urbana-Champaign)

10:15 – 11 a.m.

Reinforcement Learning in Feature Space: Complexity and Regret

Mengdi Wang (Princeton University)

11 – 11:30 a.m.

Break

11:30 a.m. – 12:15 p.m.

Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes

Alekh Agarwal (Microsoft Research Redmond)

12:15 – 2:15 p.m.

Lunch

2:15 – 3 p.m.

Off-policy Policy Optimization

Dale Schuurmans (Google Brain & University of Alberta)

3 – 3:45 p.m.

Reinforcement Learning in Recommender Systems: Some Challenges

Craig Boutilier (Google and University of Toronto)

3:45 – 4:15 p.m.

Break

4:15 – 5 p.m.

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)

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:15 a.m.

Reinforcement Learning via an Optimization Lens

Lihong Li (Google Brain)

10:15 – 11 a.m.

Towards Verified Deep Learning

Sanjit Seshia (UC Berkeley)

11 – 11:30 a.m.

Break

11:30 a.m. – 12:15 p.m.

Integrating Constraints into Deep Learning Architectures with Structured Layers

Zico Kolter (CMU Bosch)

12:15 – 2:15 p.m.

Lunch

2:15 – 3 p.m.

The Measure and Mismeasure of Fairness

Sharad Goel (Stanford University)

3 – 3:45 p.m.

Procurement as Policy: Administrative Process For Machine Learning

Deirdre Mulligan (UC Berkeley)

3:45 – 4:15 p.m.

Break

4:15 – 5 p.m.

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)

10:15 – 10:45 a.m.

Coffee and Check-In

10:45 – 11:30 a.m.

Inherent Trade-offs with the Local Explanations Paradigm

Julius Adebayo (MIT)

11:30 a.m. – 12:15 p.m.

How to Fail Interpretability Research

Been Kim (Google Brain)

12:15 – 2:15 p.m.

Lunch

2:15 – 3 p.m.

Better Learning from the Past: Counterfactual / Batch RL

Emma Brunskill (Stanford University)

3 – 3:45 p.m.

Designing Robust Learners

Jacob Steinhardt (Stanford University)