77 citations · 107 across the 3 of their papers we have counts for
3 papers
Deep Exponential Families
Rajesh Ranganath, Linpeng Tang, Laurent Charlin +1
We describe \textit{deep exponential families} (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep neural networks. DEFs capture a hie…
Active Learning for Matching Problems
Laurent Charlin, Rich Zemel, Craig Boutilier
Effective learning of user preferences is critical to easing user burden in various types of matching problems. Equally important is active query selection to further reduce the am…
Hierarchical POMDP Controller Optimization by Likelihood Maximization
Marc Toussaint, Laurent Charlin, Pascal Poupart
Planning can often be simpli ed by decomposing the task into smaller tasks arranged hierarchically. Charlin et al. [4] recently showed that the hierarchy discovery problem can be f…