On April 24 2017, 5th International Conference on Learning Representations held in Toulon, France. It's a conference  focused on how one can learn meaningful and useful representations of data for Machine Learning.

ICLR includes conference and workshop tracks, with invited talks along with oral and poster presentations of some of the latest research on deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization.

There are totally 490 contributions and ultimately 15 oral papers and 181 poster papers are included.

Next list some papers:

Understanding Deep Learning Requires Rethinking Generalization (Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals)

Semi-Supervised Knowledge Transfer for Deep Learning from Private Training Data (Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal Talwar)

Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic (Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine)

Neural Architecture Search with Reinforcement Learning (Barret Zoph, Quoc Le)


link: https://research.googleblog.com/2017/04/research-at-google-and-iclr-2017.html