In diverse world of deep learning research has given rise to numerous architectures for neural networks (convolutional ones, long short term memory ones, etc). However, to this date, the underlying training algorithms for neural networks are still stochastic gradient descent (SGD) and its heuristic variants. In this paper, we address the problem of designing a new algorithm that has provably faster running time than the best known result for SGD.

This is unfortunate since the safety afforded by Bayesian statistics is extremely valuable in many prominent mobile applications. For example, the cost of erroneous decisions are very high in autonomous driving or mobile robotic control.

Neural Information Processing Systems http://nips.cc/

The planners use representation-specific algorithms, thus allowing themselves to be run on all domains that can be expressed in the representation.

Neural Information Processing Systems http://nips.cc/

Time series are ubiquitous in many classification/regression applications.

Knowing when a classifier's prediction can be trusted is useful in many applications

Generalization has been one of the major challenges for learning dynamics models in model-based reinforcement learning.

In a number of disciplines, the data (e.g., graphs, manifolds) to be analyzed are

In this paper, we propose a generative multi-column network for image inpainting.