Two key properties of covariance functions are stationarity and monotony .

Tensor regression has been widely studied in the literature.

The complexity of the traditional LP solver is still at least quadratic in the problem dimension, i.e., the

Despite their theoretical appeal, the applicability of these methods to real data is still limited due to a lack of robustness to model misspecification. In this paper we present a hierarchical approach to methods of moments to circumvent such limitations.

We make progress on both computational and statistical aspects of the problem.

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

Maximum likelihood for LDS estimation, on the other hand, has several advantages.

For example, why does a deep neural network assign an image to a particular class? We cast interpretability of black-box classifiers as a combinatorial maximization problem and propose an efficient streaming algorithm to solve it subject to cardinality constraints.

This game continues until the agent reaches a final state and receives a terminal reward .

The new space might have more or fewer dimensions depending on the goal.