432 citations · 1.2k across the 38 of their papers we have counts for
4 papers · 1 filter
Gradient Estimation with Stochastic Softmax Tricks
Max B. Paulus, Dami Choi, Daniel Tarlow +2
The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to larg…
Fast Training of Sparse Graph Neural Networks on Dense Hardware
Matej Balog, Bart van Merriënboer, Subhodeep Moitra +2
Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by…
Batch Policy Gradient Methods for Improving Neural Conversation Models
Kirthevasan Kandasamy, Yoram Bachrach, Ryota Tomioka +2
We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automate…
Detecting Parameter Symmetries in Probabilistic Models
Robert Nishihara, Thomas Minka, Daniel Tarlow
Probabilistic models often have parameters that can be translated, scaled, permuted, or otherwise transformed without changing the model. These symmetries can lead to strong correl…