CSML Reading Group

Join

To subscribe to our listserv and receive weekly email reminders about meetings:

Send an email to listserv [at] princeton.edu from the email you wish to have subscribed.
In the body of the email, write: SUB SMLPapers FirstName LastName

The subject should be blank. For more information, please see: helpdesk.princeton.edu

2019 Meetings

Date	Presenter	Topic	Reading
Sept. 27	Michael Guerzhoy Slides	Organizational matters A refresher on Q-learning	Ch. 6 of Sutton and Barto Mnih et al, Human-level control through deep reinforcement learning (Nature, 2015)
Oct. 7	Michael Guerzhoy	Introductory meeting, take 2 (repeat of Sept. 27)
Oct 11	Michael Guerzhoy Slides	Non-delusional Q-Learning (winner, Best Paper Award at NeurIPS 2018)	Lu et al., Non-delusional Q-learning and value-iteration (NeurIPS 2018)
Oct. 18	Ryan Lee	Generative Adversarial Networks	Goodfellow, Generative Adversarial Networks tutorial
Oct. 25	Michael Guerzhoy	Wasserstein GAN	Arjovsky et al, Wasserstein GAN
Nov. 1	Ryan Lee	Neural Machine Translation by Jointly Learning to Align and Translate	Bahdanau et al, Neural Machine Translation by Jointly Learning to Align and Translate

Past Meetings

Date	Presenter	Topic	Reading
Random matrices
05/03/18	Adam Charles	Matrix concentration inequalities; application: short-term memory of linear recurrent neural networks	Joel Tropp. User-friendly tail bounds for sums of random matrices Charles, Yin, and Rozell. Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
04/26/18	Mikio Aoi	Random projections for least squares	Michael W. Mahoney. Lecture Notes on Randomized Linear Algebra, chapters 6–7.
04/19/18	Farhan Damani	Low-rank matrix approximation	Michael W. Mahoney. Lecture Notes on Randomized Linear Algebra, chapters 14–15.
04/12/18	Greg Darnell	Markov, Chebyshov, and Chernoff's inequalities; Johnson–Lindenstrauss lemma	Michael W. Mahoney. Lecture Notes on Randomized Linear Algebra, chapters 4–5.
04/05/18	Bianca Dumitrascu	Motivation for random matrices; intro on concentration inequalities	Michael W. Mahoney. Lecture Notes on Randomized Linear Algebra, chapter 3 (optional: chapters 1–2).
Information geometry
03/15/18	Jordan Ash, Alex Beatson	The Fisher-Rao metric and generalization of neural networks	Constantino Tsallis. Fisher-Rao Metric, Geometry, and Complexity of Neural Networks Ferenc Huszár. Generalization and the Fisher-Rao norm
03/01/18	Sidu Jena	Information entropy and max entropy methods	Constantino Tsallis. Possible Generalization of Boltzmann-Gibbs Statistics
02/08/18	Diana Cai, Bianca Dumitrascu	Natural gradients, mirror descent and stochastic variational inference	Shun'ichi Amari. Information geometry and its applications, chapter 12. Garvesh Raskutti, Sayan Mukherjee. The Information Geometry of Mirror Descent. Matthew D. Hoffman, David M. Blei, Chong Wang, John Paisley. Stochastic Variational Inference.
02/08/18	Alex Beatson, Greg Gundersen	Intro: information geometry, f-divergences, the Fisher metric, and the exponential family	Shun'ichi Amari. Information geometry and its applications, chapters 2-3. John Baez' intro to information geometry: Information Geometry.
01/25/18	Sidu Jena, Archit Verma	Differential geometry overview	Shun'ichi Amari. Information geometry and its applications, chapters 1, 5, and 6. Encyclopedia of Mathematics: Differential Geometry.
Reinforcement learning & control theory
11/16/17	Archit Verma	Robust Control	Leo Rollins. Robust Control Theory, course notes from Dependable Embedded Systems @ CMU. 1999. Robbie D’Angelo and Sam Safavi. Robust Control, course notes from Advanced Control of Complex Dynamical Systems @ Tufts. 2013. Interpretation of H-Infinity norm, from Mathworks E. Gallestey and P. Al-Hokayem. Lyapunov based control, course notes from Nonlinear Systems and Control @ ETH Zurich. 2014.
11/09/17	Ari Seff	Optimal Control	E. Gallestey and P. Al-Hokayem. Optimal control and dynamic programming, course notes from Nonlinear Systems and Control course @ ETH Zurich. 2015. Lawrence C. Evans. An Introduction to Mathematical Optimal Control Theory. Course notes
11/02/17	Sidu Jena, Max Wilson	Control Theory Basics	Lawrence C. Evans. An Introduction to Mathematical Optimal Control Theory. Course notes A. Astolfi. Systems and Control Theory An Introduction. 2006. R. Matthew Kretchmar. A synthesis of reinforcement learning and robust control theory. Dissertation: Colorado State University. 2000.
10/26/17	Alex Beatson	Actor-Critic	Sutton, R. S., McAllester, D. A., Singh, S. P., & Mansour, Y. (2000). Policy gradient methods for reinforcement learning with function approximation. In Advances in Neural Information Processing Systems (pp. 1057-1063). Schulman, John, Philipp Moritz, Sergey Levine, Michael I. Jordan, and Pieter Abbeel. High-Dimensional Continuous Control Using Generalized Advantage Estimation. International Conference on Learning Representations (ICLR). 2016. Gu, Shixiang, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, and Sergey Levine. Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic. International Conference on Learning Representations (ICLR). 2017.
10/19/17	Niranjani Prasad, Gregory Gundersen	Q-Learning	Watkins, C. J., & Dayan, P. (1992). Q-learning. Machine learning, 8(3-4), 279-292. Riedmiller, M. (2005). Neural fitted Q iteration-first experiences with a data efficient neural reinforcement learning method. In ECML (Vol. 3720, pp. 317-328). Mnih, Volodymyr, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves et al. Human-level control through deep reinforcement learning. Nature 518, no. 7540 (2015): 529-533. Lillicrap, Timothy P., Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015).
10/12/17	Ryan Adams	Policy Gradient Methods	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8(3-4), 229-256.[The paper that introduces REINFORCE.] Peters, J., & Schaal, S. (2008). Reinforcement learning of motor skills with policy gradients. Neural networks, 21(4), 682-697. [Accessible introduction to policy gradients.] Schulman, J., Levine, S., Abbeel, P., Jordan, M., & Moritz, P. (2015). Trust region policy optimization. In Proceedings of the 32nd International Conference on Machine Learning (ICML-15) (pp. 1889-1897).
Misc. previous topics
6/22	David Zoltowski, Mikio Aoi		Stochastic Gradient Descent as Approximate Bayesian Inference Mandt, Hoffman, Blei (2017)
6/1	Stephen Keeley		Understanding deep convolutional networks Mallat (2016)
5/25	Davit Zoltowski		Variational Inference with Normalizing Flows Rezende, Mohamed (2016)
5/11	Jordan Ash		Generative Adversarial Nets Ian J. Goodfellow∗ , Jean Pouget-Abadie† , Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair‡ , Aaron Courville, Yoshua Bengio§
5/4	Greg Darnell		Convolutional Neural Networks Analyzed via Convolutional Sparse Coding Vardan Papyan, Yaniv Romano, Michael Elad (2016)
4/27	Bianca Dumitrascu		Why does deep learning work so well? Henry W. Lin, Max Tegmark (2017)
4/20	Yuki Shiraito		Dropout as Bayesian approximation: Representing Model Uncertainty in Deep Learning Gal & Ghahramani (2016)
4/13	Mikio Aoi		A Probabilistic Theory of Deep Learning Ankit B. Patel, Tan Nguyen, Richard G. Baraniuk (2015)
3/30	Brian DePasquale		Semi-supervised Learning with Deep Generative Models Diederik P. Kingma, Danilo J. Rezende, Shakir Mohamed, Max Welling
3/16	Adam Charles		On the expressive power of deep learning: A tensor analysis Cohen, Sharir, Shashua (2016)
3/9	Mikio Aoi		Auto-Encoding Variational Bayes Kingma, Welling (2014)
3/2	Bianca Dumitrascu		Stochastic Backpropagation and Approximate Inference in Deep Generative Models Danilo Jimenez Rezende, Shakir Mohamed, Daan Wierstra (2014)
2/16	Nick Roy		Understanding deep learning requires rethinking generalization Zhang, Bengio, Hardt, Recht, Vinyals (2017)

Join

2019 Meetings

Past Meetings

Random matrices

Information geometry

Reinforcement learning & control theory

Misc. previous topics