If you wish to present or propose a paper, please email me (alepro@kth.se).

Wednesday February 1, 2017: Deep Learning without Poor Local Minimum (K. Kawaguchi, NIPS 2016), Slides (A. Proutiere)

Wednesday February 8, 2017: Improved Dropout for Shallow and Deep Learning (Z. Li et al., NIPS 2016), Presentation by Jaron Sanders

Wednesday February 15, 2017: The Price of Privacy in Untrusted Recommender Systems (S. Banerjee, N. Hegde, L. Maousslie) IEEE JSTSP 2015. Presentation by Rami Mochaourab

Wednesday March 1, 2017: Why does deep and cheap learning work so well?, H.W. Lin and M. Tegmark, 2016. Presentation by Joakim Jalden

Wednesday March 15, 2017: Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning (C. Dann, E. Brunskill)> Presentation by Sadegh Talebi available at: