17
0

Robust Max Entrywise Error Bounds for Tensor Estimation from Sparse Observations via Similarity Based Collaborative Filtering

Abstract

Consider the task of estimating a 3-order n×n×nn \times n \times n tensor from noisy observations of randomly chosen entries in the sparse regime. We introduce a similarity based collaborative filtering algorithm for estimating a tensor from sparse observations and argue that it achieves sample complexity that nearly matches the conjectured computationally efficient lower bound on the sample complexity for the setting of low-rank tensors. Our algorithm uses the matrix obtained from the flattened tensor to compute similarity, and estimates the tensor entries using a nearest neighbor estimator. We prove that the algorithm recovers a finite rank tensor with maximum entry-wise error (MEE) and mean-squared-error (MSE) decaying to 00 as long as each entry is observed independently with probability p=Ω(n3/2+κ)p = \Omega(n^{-3/2 + \kappa}) for any arbitrarily small κ>0\kappa > 0. More generally, we establish robustness of the estimator, showing that when arbitrary noise bounded by ε0\varepsilon \geq 0 is added to each observation, the estimation error with respect to MEE and MSE degrades by poly(ε)\text{poly}(\varepsilon). Consequently, even if the tensor may not have finite rank but can be approximated within ε0\varepsilon \geq 0 by a finite rank tensor, then the estimation error converges to poly(ε)\text{poly}(\varepsilon). Our analysis sheds insight into the conjectured sample complexity lower bound, showing that it matches the connectivity threshold of the graph used by our algorithm for estimating similarity between coordinates.

View on arXiv
Comments on this paper