We study the problem of completing a binary matrix in an online learning setting. On each trial we predict a matrix entry and then receive the true entry. We propose a Matrix Exponentiated Gradient algorithm [1] to solve this problem. We provide a mistake bound for the algorithm, which scales with the margin complexity [2, 3] of the underlying matrix. The bound suggests an interpretation where each row of the matrix is a prediction task over a finite set of objects, the columns. Using this we show that the algorithm makes a number of mistakes which is comparable up to a logarithmic factor to the number of mistakes made by the Kernel Perceptron with an optimal kernel in hindsight. We discuss applications of the algorithm to predicting as well as the best biclustering and to the problem of predicting the labeling of a graph without knowing the graph in advance.

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

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

Taiwan President Lai Ching-te has cancelled a presidential trip to the African nation of Eswatini, accusing Beijing of putting pressure on its neighbours to bar his aircraft from flying over their territories. Seychelles, Mauritius and Madagascar revoked Lai's overflight permits after intense pressure and economic coercion from China, said a Taiwan official. China denied coercion, while praising the three African countries saying it had high appreciation for them. This is the first publicly known instance where a Taiwanese leader has had to cancel a foreign trip due to revoked flight permits. Eswatini, formerly known as Swaziland, is Taiwan's only diplomatic ally in Africa.

Save on iRobot products, including robot vacuums and mops designed to handle pet hair, daily messes, and hands-free cleaning with smart home integration. The brand iRobot launched the first Roomba robot vacuum back in 2002, and popularity for the handy devices skyrocketed from there. Countless competitors have emerged, but Roomba is still going strong. Its latest models have all the new features we love, from doubling as a vacuum and a mop to fantastic navigation and suction. The Roomba Max 705 is currently keeping my house clean as I test it for our robot vacuum guide, and it's doing a great job both mopping and vacuuming the floors in my massive second story.

This paper deals with price optimization, which is to find the best pricing strategy that maximizes revenue or profit, on the basis of demand forecasting models. Though recent advances in regression technologies have made it possible to reveal price-demand relationship of a large number of products, most existing price optimization methods, such as mixed integer programming formulation, cannot handle tens or hundreds of products because of their high computational costs. To cope with this problem, this paper proposes a novel approach based on network flow algorithms. We reveal a connection between supermodularity of the revenue and cross elasticity of demand. On the basis of this connection, we propose an efficient algorithm that employs network flow algorithms. The proposed algorithm can handle hundreds or thousands of products, and returns an exact optimal solution under an assumption regarding cross elasticity of demand. Even if the assumption does not hold, the proposed algorithm can efficiently find approximate solutions as good as other state-of-the-art methods, as empirical results show.

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

The U.S. military is launching a new autonomous warfare command under SOUTHCOM to deploy unmanned systems across Latin America, SOUTHCOM Gen. Francis Donovan said.

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate endto-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.