Authors Title
Christopher Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Mohammad Norouzi, Andriy Mnih, Arnaud Doucet and Yee Whye Teh.  Filtering Variational Objectives
George Tucker, Andriy Mnih, Chris J. Maddison, Dieterich Lawson and Jascha Sohl-Dickstein.  REINFORCing Concrete with REBAR
Rémi Leblond, Jean-Baptiste Alayrac, Anton Osokin and Simon Lacoste-Julien.  SEARNN : Training RNNs with global-local losses
David Belanger and Andrew McCallum.  Randomized SPENs for Multi-Modal Prediction
Po-Sen Huang, Chong Wang, Dengyong Zhou and Li Deng.  Toward Neural Phrase-based Machine Translation
Dung Thai, Shikhar Murty, Trapit Bansal, Luke Vilnis, David Belanger and Andrew McCallum.  Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling
Wu Lin, Mohammad Emtiyaz Khan, Nicolas Hubacher and Didrik Nielsen.  Natural-Gradient Stochastic Variational Inference for Non-Conjugate Structured Variational Autoencoder
Jason Naradowsky and Sebastian Riedel.  Modeling Exclusion with a Differentiable Factor Graph Constraint
Yinchong Yang, Volker Tresp and Peter Fasching.  Modeling Clinical Decisions with Multinomial Hierarchical Classification
Stephan Zheng, Rose Yu and Yan Liu.  Learning Chaotic Dynamics using Tensor Recurrent Neural Networks
Dan Goldwasser, Jennifer Neville, Yi-Yu Lai and Chang Li.  Joint Embedding Models for Textual and Social Analysis
Xiang Li, Luke Vilnis and Andrew McCallum.  Improved Representation Learning for Predicting Commonsense Ontologies
Pablo Rozas Larraondo, Inaki Inza and Jose Antonio Lozano.  Automating weather forecasts based on convolutional networks
Hao Liu, Xinyi Yang and Zenglin Xu.  Structured Neural Turing Machine
Joel Ruben Antony Moniz and Christopher Pal.  Deep Convolutional Networks with Non-convolutional Recurrent Memory for Structured Prediction
Xinyi Yang, Hao Liu and Zenglin Xu.  Variational Structured Stochastic Network
Lev Faivishevsky and Amitai Armon.  Deep structured modeling of deep learning training convergence with application to hyperparameter optimization
Heejin Choi and Karl Stratos  Handling Large Structural Costs in Neural Networks with Slack Rescaling