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

Heuristic tools from statistical physics have been used in the past to locate the phase transitions and compute the optimal learning and generalization errors in the teacher-student scenario in multi-layer neural networks. In this contribution, we provide a rigorous justification of these approaches for a two-layers neural network model called the committee machine.

We propose and study the problem of distribution-preserving lossy compression.

Graph-structured data arise in wide applications, such as computer vision, bioinfor-matics, and social networks. Quantifying similarities among graphs is a fundamental problem.

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This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .

We consider the problem of learning a low dimensional representation for compositional data.

The computational complexity of a property tester is the number of adjacency list entries it reads, denoted its queries . Many works in graph property testing focus on testing plain graphs that contain only the pure combinatorial information.

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

We analyze linear independence of rank one tensors produced by tensor powers of randomly perturbed vectors. This enables efficient decomposition of sums of high-order tensors. Our analysis builds upon Bhaskara et al.