We propose a sparse and low-rank tensor regression model to relate a univariate outcome to a feature tensor, in which each unit-rank tensor from the CP decomposition of the coefficient tensor is assumed to be sparse.

In fact, the additive noise model assumes that all categories of the variables are placed in the "right" order; furthermore, if

To mitigate the threat of adversarial examples, a large number of methods have been developed.

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions.

Coordinated counterterrorism raids across Germany and Austria, with Mossad and European agencies working together, uncover Hamas network planning attacks on Israeli and Jewish civilians.

Breakthroughs, discoveries, and DIY tips sent every weekday. Nearly one in three U.S. households harbor a cold-hearted killer. Some even have a well-known proclivity for torture. And while the popular pets are best known for downing birds and cornering mice, they are also adept at hunting all manner of bugs. Host a cat in your home long enough and you'll likely become accustomed to regular deliveries of amputated insect legs, wings, or the occasional whole carcass.

Although much theoretical analysis has been performed to understand the practical behavior of SGD and SCMD, the existing theoretical results are still not quite satisfactory. Firstly, most of the existing theoretical results are stated in expectation which inevitably ignore some information on high-order moments of the random variable we are interested in.

Learning problems of this scale are often referred to as extreme classification .

Recent work on generating adversarial attacks have shown that it is computationally feasible for a bad actor to fool a DRL policy into behaving sub optimally.

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