Introduction
The Machine Learning Reading Group (MLRG) meets weekly to talk about recent research in a particular field which is chosen at the begining of each semester. The current focus is on causality, bandits, and reinforcement learning.
Subscription
To receive announcements about the reading group, please join our mailing list by sending "subscribe mlrg-l YOUR-EMAIL-ADDRESS" in the message body to majordomo@cs.ubc.ca.
Update
The current MLRG web page is hosted here MRLG 2015-16
Organization
We meet every Tuesday, 4:00 to 5:00 in room X836.
The current organizers are Michael Gelbart,
Alireza Shafaei
, and Mark Schmidt.
On the following days our meeting will be at a differnet location:
- January 20th ICCS 146
You can also automatically update your MyCS calendar by subscribing to the MLRG events here.
Presentation Signup List
The following people have volunteered to present at MLRG this semester.
Name | Date | Name | Date |
| Jan 20 | | Mar 17 |
| Jan 27 | Mar 24 | |
| Feb 3 | | Mar 31 |
| Feb 10 | Apr 1 | |
| Feb 24 | Apr 14 | |
| Mar 3 | → Djallel Bouneffouf | Apr 28 |
| Mar 10 |
Current Semester
-
Apr 14, 2015
Mehran Kazemi presented: Guestrin, Carlos, et al. "Generalizing plans to new environments in relational MDPs" In Proceedings of International Joint Conference on Artificial Intelligence. 2003..
[PDF] -
Mar 31, 2015
Michiel van de Panne presented: Reinforcement Learning in Graphics.
-
Mar 24, 2015
Nasim Zolaktaf presented: Toulis, Panos, and Edward Kao. "Estimation of causal peer influence effects" Proceedings of The 30th International Conference on Machine Learning. 2013.
[JMLR] -
Mar 17, 2015
Ankur Gupta presented: Patrik O. Hoyer, Dominik Janzing, Joris M. Mooij, Jonas Peters, Bernhard Schölkopf. "Nonlinear causal discovery with additive noise models" Advances in Neural Information Processing Systems. 2008.
[NIPS] -
Mar 10, 2015
Reza Babanezhad presented: Amir Sani, Gergely Neu, and Alessandro Lazaric. "Exploiting easy data in online optimization" Advances in Neural Information Processing Systems. 2014.
[NIPS] -
Mar 3, 2015
Alireza Shafaei presented: Luo, Haipeng, and Robert E. Schapire. "A drifting-games analysis for online learning and applications to boosting" Advances in Neural Information Processing Systems. 2014.
[NIPS] -
Feb 24, 2015
Alim Virani presented: Abbeel, Pieter, et al. "An application of reinforcement learning to aerobatic helicopter flight" Advances in neural information processing systems 19 (2007): 1.
[PDF] -
Feb 10, 2015
Jason Hartford presented: Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning" arXiv preprint arXiv:1312.5602 (2013).
[arXiv] -
Feb 3, 2015
Neil Traft presented: Ng, Andrew Y., and Stuart J. Russell. "Algorithms for inverse reinforcement learning" ICML 2000.
[PDF] -
Jan 27, 2015
Sharan Vaswani presented: An introduction to bandits.
-
Jan 20, 2015
Issam Laradji presented: An introduction to reinforcement learning.
[Slides] [Supplementary Material (CS 422)] -
Jan 13, 2015
Mark Schmidt presented: Judea Pearl "Causality": An introduction.
[Book]
Fall 2014
Our previous focus was on Bayesian Optimization and Deep Learning.-
Dec 16, 2014
Julieta Martinez presents: Lenc K. and Vedaldi, A. "Understanding image representations by measuring their equivariance and equivalence" arXiv. 2014.
[arXiv] -
Dec 2, 2014
Mark Schmidt presents: Adam Bull. "Convergence Rates for Efficient Global Optimization Algorithms" The Journal of Machine Learning Research 12 (2011): 2879-2904.
[JMLR] -
Nov 25, 2014
Glenn Bevilacqua presents: Chapelle, Olivier, and Lihong Li. "An Empirical Evaluation of Thompson Sampling" Advances in Neural Information Processing Systems. 2011.
[NIPS] -
Nov 18, 2014
Reza Babanezhad presents: Julien Villemonteix, Emmanuel Vazquez, and Eric Walter. "An informational approach to the global optimization of expensive-to-evaluate functions." Journal of Global Optimization 44.4 (2009): 509-534.
[arXiv] -
Nov 4, 2014
Bita Nejat presents: Niranjan Srinivas, Andreas Krause, Sham Kakade and Matthias Seeger. "Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design." arXiv prepring arXiv:0912.3995.
[arXiv] -
Oct 28, 2014
Sharan Vaswani presents: Duvenaud, David, Oren Rippel, Ryan P. Adams, and Zoubin Ghahramani. "Avoiding pathologies in very deep networks." arXiv prepring arXiv:1402.5836.
[arXiv] -
Oct 14, 2014
Anurag Ranjan presents: Lei Jimmy Ba, Rich Caruana. "Do Deep Nets Really Need to be Deep?" arXiv prepring arXiv:1312.6184.
[arXiv] -
Oct 07, 2014
Hamid Palangi presents: Hochreiter, Sepp, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9.8 (1997): 1735-1780.
[PDF] -
Sep 30, 2014
Michael Gelbart presents: Szegedy, Christian, et al. "Intriguing properties of neural networks" arXiv preprint arXiv:1312.6199 (2013).
[arXiv] -
Sep 30, 2014
Alireza Shafaei presents: Szegedy, Christian, et al. "Going Deeper with Convolutions" arXiv preprint arXiv:1409.4842 (2014).
[arXiv] -
Sep 23, 2014
Alireza Shafaei presents: An introduction to Convolutional Neural Networks.
[Lazebnik's Lecture Slides] -
Sep 16, 2014
Michael Gelbart presents: Jasper Snoek, Hugo Larochelle, and Ryan P. Adams. "Practical Bayesian optimization of machine learning algorithms" NIPS. 2012.
[NIPS Page]