October 11, 2018 - BayLearn 2018 Symposium
To watch all the videos in order, please visit our YouTube Playlist for BayLearn 2018
8:00am
|
Registration opens
|
8:00am - 9:00am
|
Coffee & Light Breakfast
|
9:05am
|
Welcome to BayLearn 2018! Jerremy Holland, Apple Inc. | |
Welcome to Facebook Joaquin Quiñonero Candela, Facebook.
|
| |
|
9:15am
|
Keynote 1
|
Data-Driven Dialogue Systems: Models, Algorithms, Evaluation, and Ethical Challenges
Joelle Pineau, Facebook & McGill University |
|
|
10:00am
Chair: Jerremy Holland
|
Session 1
|
Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
George Tucker, Dieterich Lawson, Chris J Maddison abstract.pdf |
|
Local Linear Forests: Leveraging Smoothness with Random Forests
Rina S Friedberg, Julie Tibshirani, Susan Athey, Stefan Wager abstract.pdf |
|
Deep Learning for Supercomputers
Noam M Shazeer, Youlong Cheng, Niki Parmar, Dustin Tran, Ashish Vaswani, Penporn Koanantakool, Peter Hawkins, HyoukJoong Lee, Mingsheng Hong, Cliff Young, Ryan Sepassi, Blake Hechtman abstract.pdf |
|
|
10:45am - 11:10am
|
Break
|
11:15am
|
Keynote 2
|
Some representation, optimization and generalization properties of deep networks
Peter Bartlett, CS and Statistics, UC Berkeley |
|
|
12:00pm
Chair: Jean-Francois Paiement
|
Session 2
|
A Deep Generative Model for Semi-Supervised Classification with Noisy Labels
Maxime Langevin abstract.pdf |
|
Improved Mixed-Example Data Augmentation
Cecilia Summers abstract.pdf |
|
|
12:30pm - 1:50pm
|
Lunch
|
2:00pm
|
Keynote 3
|
Statistical and machine learning challenges from genetics to CRISPR gene editing
Jennifer Listgarten, Center for Computational Biology & Berkeley AI Research, UC Berkeley |
|
|
2:45pm
Chair: Isabelle Guyon
|
Session 3
|
Plannable Representations with Causal InfoGAN
Thanard Kurutach, Aviv Tamar abstract.pdf |
|
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
Kurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine abstract.pdf |
|
|
3:15pm - 3:40pm
|
Break
|
3:45pm
Chair: David Grangier
|
Keynote 4
|
What's Wrong with Meta-Learning (and how we can fix it)
Sergey Levine, Berkeley AI Research Lab, UC Berkeley and Google |
|
|
4:45pm
|
Main Poster Session, Prizes, Food and Refreshments
|
7:00pm
|
End of the Symposium
|
|
|