Recovery Guarantees For Quadratic Tensors With Sparse Observations
[edit]
Proceedings of Machine Learning Research, PMLR 89:33223332, 2019.
Abstract
We consider the tensor completion problem of predicting the missing entries of a tensor. The commonly used CP model has a triple product form, but an alternate family of quadratic models which are the sum of pairwise products instead of a triple product have emerged from applications such as recommendation systems. Nonconvex methods are the method of choice for learning quadratic models, and this work examines their sample complexity and error guarantee. Our main result is that with the number of samples being only linear in the dimension, all local minima of the mean squared error objective are global minima and recover the original tensor. We substantiate our theoretical results with experiments on synthetic and realworld data.
Related Material


