A reciprocal recommendation problem is one where the goal of learning is not just to predict a user's preference towards a passive item (e.g., a book), but to

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

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

Equal Contribution 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada. is often attributed to the rapid decay in the learning rate when gradients are dense, which is often the case in many machine learning applications.

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

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 .

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.

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

How to learn, while ensuring that a spying adversary does not learn?