A Dual Framework for Low-rank Tensor Completion

Neural Information Processing Systems

One of the popular approaches for low-rank tensor completion is to use the latent trace norm regularization. However, most existing works in this direction learn a sparse combination of tensors. In this work, we fill this gap by proposing a variant of the latent trace norm that helps in learning a non-sparse combination of tensors. We develop a dual framework for solving the low-rank tensor completion problem.





Contextual Stochastic Block Models

Neural Information Processing Systems

We provide the first information theoretic tight analysis for inference of latent community structure given a sparse graph along with high dimensional node covariates, correlated with the same latent communities.


The streaming rollout of deep networks - towards fully model-parallel execution

Neural Information Processing Systems

Deep neural networks, and in particular recurrent networks, are promising candidates to control autonomous agents that interact in real-time with the physical world. However, this requires a seamless integration of temporal features into the network's architecture. For the training of and inference with recurrent neural networks, they are usually rolled out over time, and different rollouts exist.


Interactive Structure Learning with Structural Query-by-Committee

Neural Information Processing Systems

In this work, we introduce interactive structure learning, a framework that unifies many different interactive learning tasks. We present a generalization of the queryby-committee active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically and empirically, with and without noise.