Country
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
Mahmoud ("Mido") Assran, Joshua Romoff, Nicolas Ballas, Joelle Pineau, Mike Rabbat
Neural Information Processing Systems http://nips.cc/
Improving Neural Program Synthesis with Inferred Execution Traces
Eui Chul Shin, Illia Polosukhin, Dawn Song
Neural Information Processing Systems http://nips.cc/
On the Global Convergence of (Fast) Incremental Expectation Maximization Methods
Belhal Karimi, Hoi-To Wai, Eric Moulines, Marc Lavielle
Neural Information Processing Systems http://nips.cc/
Automatic differentiation in ML: Where we are and where we should be going
Bart van Merrienboer, Olivier Breuleux, Arnaud Bergeron, Pascal Lamblin
Firstly, many machine learning models use optimization algorithms which require access to derivatives of the model.
