January 26 – 30, 2015 Workshop on Big Data and Statistical Machine Learning
Organizing Committee
Ruslan Salakhutdinov (Chair) Dale Schuurmans Yoshua Bengio	Hugh Chipman Bin Yu

Registration for Workshop on-site January 26 $150 registration fees, $50 students and PDF		Application for Participant support deadline to apply March 1, 2015	Reimbursement information for funded participants
Back to main index	Confirmed Workshop Participants	Accommodation in Toronto	Information for speakers

Program

The aim of this workshop is to bring together researchers working on various large-scale deep learning as well as hierarchical models to discuss a number of important challenges, including the ability to perform transfer learning as well as the best strategies to learn these systems on large scale problems. These problems are "large" in terms of input dimensionality (in the order of millions), number of training samples (in the order of 100 millions or more) and number of categories (in the order of several tens of thousands).

Tentative Schedule

Monday January 26
8:30-9:15	Coffee and Registration
9:15-9:30	Ruslan Salakhutdinov: Welcome
9:30-10:30	Yoshua Bengio, Université de Montréal Exploring alternatives to Boltzmann machine
10:30-11:00	Coffee
11:00-12:00	John Langford, Microsoft Research Learning to explore
12:00-2:00	Lunch
2:00-3:00	Hau-tieng Wu, University of Toronto Structure massive data by graph connection Laplacian and its application
3:00-3:30	Tea
3:30-4:30	Roger Grosse, University of Toronto Scaling up natural gradient by factorizing Fisher information
4:30	Cash Bar Reception
Tuesday January 27
9:30-10:30	Brendan Frey, University of Toronto The infinite genome project: Using statistical induction to understand the genome and improve human health
10:30-11:00	Coffee break
11:00-12:00	Daniel Roy, University of Toronto Mondrian Forests: Efficient Online Random Forests
12:00-2:00	Lunch break
2:00-3:00	Raquel Urtasun, University of Toronto
3:00-3:30	Tea break
Wednesday January 28
9:30-10:30	Samy Bengio, Google Inc The Battle Against the Long Tail
10:30-11:00	Coffee break
11:00-12:00	Richard Zemel, University of Toronto Learning Rich But Fair Representations
12:00-1:00	Lunch break
2:00-3:00	David Blei, Princeton University Probabilistic Topic Models and User Behavior
3:00-3:30	Tea break
3:30-4:30	Yura Burda, Fields Institute Raising the Reliability of Estimates of Generative Performance of MRFs
Thursday January 29
9:30-10:30	Joelle Pineau, McGill University Practical kernel-based reinforcement learning
10:30-11:00	Coffee break
11:00-12:00	Cynthia Rudin, MIT CSAIL and Sloan School of Management Thoughts on Interpretable Machine Learning
12:00-2:00	Lunch
2:00-3:00	Radford Neal, University of Toronto Learning to Randomize and Remember in Partially-Observed Environments
3:00-3:30	Tea break
Friday January 30
9:30-10:30	Alexander Schwing, The Fields Institute Deep Learning meets Structured Prediction
10:30-11:00	Coffee break
11:00-12:00	Ruslan Salakhutdinov:Closing remarks.
12:00-2:00	Lunch