Stochastic/Policy Gradients in Deep Learning – ICLR 2017 Discoveries

The 5th International Conference on Learning Representation (ICLR 2017) is coming to Toulon, France (April 24-26 2017).

This blog post gives an overview of papers related to stochastic/policy gradient submitted to ICLR 2017, see underneath for the list of papers.

Best regards,
Amund Tveit

  1. Improving Policy Gradient by Exploring Under-appreciated Rewards – Authors: Ofir Nachum, Mohammad Norouzi, Dale Schuurmans
  2. Leveraging Asynchronicity in Gradient Descent for Scalable Deep Learning – Authors: Jeff Daily, Abhinav Vishnu, Charles Siegel
  3. Adding Gradient Noise Improves Learning for Very Deep Networks – Authors: Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Lukasz Kaiser, Karol Kurach, Ilya Sutskever, James Martens
  4. Inefficiency of stochastic gradient descent with larger mini-batches (and more learners) – Authors: Onkar Bhardwaj, Guojing Cong
  5. Improving Stochastic Gradient Descent with Feedback – Authors: Jayanth Koushik, Hiroaki Hayashi
  6. PGQ: Combining policy gradient and Q-learning – Authors: Brendan O’Donoghue, Remi Munos, Koray Kavukcuoglu, Volodymyr Mnih
  7. SGDR: Stochastic Gradient Descent with Restarts – Authors: Ilya Loshchilov, Frank Hutter
  8. Neural Data Filter for Bootstrapping Stochastic Gradient Descent – Authors: Yang Fan, Fei Tian, Tao Qin, Tie-Yan Liu
  9. Entropy-SGD: Biasing Gradient Descent Into Wide Valleys – Authors: Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun
  10. Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic – Authors: Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine
  11. Batch Policy Gradient Methods for Improving Neural Conversation Models – Authors: Kirthevasan Kandasamy, Yoram Bachrach, Ryota Tomioka, Daniel Tarlow, David Carter
  12. Training Long Short-Term Memory With Sparsified Stochastic Gradient Descent – Authors: Maohua Zhu, Minsoo Rhu, Jason Clemons, Stephen W. Keckler, Yuan Xie
  13. Parallel Stochastic Gradient Descent with Sound Combiners – Authors: Saeed Maleki, Madanlal Musuvathi, Todd Mytkowicz, Yufei Ding
  14. Gradients of Counterfactuals – Authors: Mukund Sundararajan, Ankur Taly, Qiqi Yan

Sign up for Deep Learning newsletter!

Continue Reading