Note: the website for the ICML 2017 offering of this workshop can be found here.

8:40 - Opening Remarks (video)

Session 1: New Challenges in Machine Learning

9:00 - Invited talk: Rules for Reliable Machine Learning. Martin Zinkevich (video)

9:30 - Contributed talk: What's your ML Test Score? A rubric for ML production systems. Eric Breck, Shanqing Cai, Eric Nielsen, Michael Salib, D. Sculley (slides) (video)

9:45 - Poster spotlights (video)

  • Towards Interactive Inverse Reinforcement Learning. Stuart Armstrong, Jan Leike
  • Active Labeling Management. Alessandro Magnani, Shie Mannor
  • Should Robots Have Off Switches? Smitha Milli, Dylan Hadfield-Menell, Stuart Russell
10:00 - Coffee break

Session 2: Robustness to Model Mis-specification

10:30 - Invited talk: Robust Learning and Inference. Yishay Mansour (video)

11:00 - Invited talk: Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competition. Jennifer Hill (video)

11:30 - Contributed talk: Robust Covariate Shift Classification Using Multiple Feature Views. Anqi Liu, Hong Wang Brian D. Ziebart (video)

11:45 - Poster spotlights (video)

  • Probabilistically Safe Policy Transfer. David Held, Zoe McCarthy, Michael Zhang, Fred Shentu, Pieter Abbeel
  • Resource-Efficient Feature Gathering at Test Time. Gavin Gray, Amos Storkey
  • Outlier Robust Distributed Learning. Jiashi Feng, Huan Xu, Shie Mannor
  • Variance Reduction for Large Scale Revenue Optimization. Andres Munoz Medina, Sergei Vassilvitskii
12:00 - Lunch

Session 3: Machine Learning and Security

1:30 - Contributed talk: Learning from Untrusted DataMoses Charikar, Jacob Steinhardt, Gregory Valiant (slides) (video)

1:45 - Invited talk: Adversarial Examples and Adversarial Training. Ian Goodfellow (video)

2:15 - Contributed talk: Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning. Rock Stevens, Octavian Suciu, Andrew Ruef, Sanghyun Hong, Michael Hicks, Tudor Dumitras (slides) (video)

2:30 - Poster spotlights (video)

  • Kernel Observers: Systems-Theoretic Modeling and Inference of Spatiotemporally Varying Processes. Hassan Kingravi, Harshal Maske, Girish Chowdhary
  • Modeling Nonlinear Dynamical Fluid Flows with Evolving Gaussian Process Models. Joshua E. Whitman, Harshal Maske, Girish Chowdhary, Hassan Kingravi, Balaji Jayaraman, Chen Lu

2:45 - 3:30 Poster session

Session 4: Reliable Robotics in Complex Environments

3:30 - Invited talk: Learning Reliable Objectives. Anca Dragan (video)

4:00 - Invited talk: Building and Validating the AI behind the Next-Generation Collision Avoidance Systems. Mykel Kochenderfer

Session 5: Reliable Machine Learning in Practice

4:30 - Contributed talk: Online Prediction with Selfish Experts. Okke Schrijvers (video)

4:45 - Contributed talk: TensorFlow Debugger: Debugging Dataflow Graphs for Machine Learning. Shanqing Cai, Eric Breck, Eric Nielsen, Michael Salib, D. Sculley (slides) (video)

5:00 - Panel discussion: What are the challenges to making ML reliable in practice?

Ian Goodfellow, D. Sculley, Anca Dragan, Martin Zinkevich, Dario Amodei