Schedule

Friday June 14, Long Beach, California, USA

8:30am - 8:40am Opening remarks
8:40am - 9:30am Spotlight presentations (paper ID 7-53)
9:30am - 10:00am Keynote by Max Welling: A Nonparametric Bayesian Approach to Deep Learning (without GPs)
10:00am-10:30am Poster session (poster session can continue during coffee break)

11am - 11:30 Keynote by Kilian Weinberger: On Calibration and Fairness
11:30am - 11:40am Contributed talk #1: Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
11:40am - 11:50am Contributed talk #2: Detecting Extrapolation with Influence Functions
11:50am - 12:00pm Contributed talk #3: How Can We Be So Dense? The Robustness of Highly Sparse Representations
12:00pm - 12:30pm Keynote by Suchi Saria Safety Challenges with Black-Box Predictors and Novel Learning Approaches for Failure Proofing

2:00pm - 2:10pm Contributed talk #4: Subspace Inference for Bayesian Deep Learning
2:10pm - 2:20pm Contributed talk #5: Quality of Uncertainty Quantification for Bayesian Neural Network Inference
2:20pm - 2:30pm Contributed talk #6: ‘In-Between’ Uncertainty in Bayesian Neural Networks
2:30pm - 3:00pm Keynote by Dawn Song: Adversarial Machine Learning: Challenges, Lessons, and Future Directions

3:30pm - 4:00pm Keynote by Terrance Boult: The Deep Unknown: on Open-set and Adversarial Examples in Deep Learning
4:00pm - 5:00pm Panel discussion (Moderator: Tom Dietterich)
5:00pm - 6:00pm Poster Session

Google Sites

Report abuse