Near-optimal sample complexity for convex tensor completion
We analyze low rank tensor completion (TC) using noisy measurements of a subset of the tensor. Assuming a rank-$r$, order-$d$, $N \times N \times \cdots \times N$ tensor where $r=O(1)$, the best sampling complexity that was achieved is $O(N^{\frac{d}{2}})$, which is obtained by solving a tensor nucl...
Saved in:
Main Authors | , , |
---|---|
Format | Journal Article |
Language | English |
Published |
14.11.2017
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | We analyze low rank tensor completion (TC) using noisy measurements of a
subset of the tensor. Assuming a rank-$r$, order-$d$, $N \times N \times \cdots
\times N$ tensor where $r=O(1)$, the best sampling complexity that was achieved
is $O(N^{\frac{d}{2}})$, which is obtained by solving a tensor nuclear-norm
minimization problem. However, this bound is significantly larger than the
number of free variables in a low rank tensor which is $O(dN)$. In this paper,
we show that by using an atomic-norm whose atoms are rank-$1$ sign tensors, one
can obtain a sample complexity of $O(dN)$. Moreover, we generalize the matrix
max-norm definition to tensors, which results in a max-quasi-norm (max-qnorm)
whose unit ball has small Rademacher complexity. We prove that solving a
constrained least squares estimation using either the convex atomic-norm or the
nonconvex max-qnorm results in optimal sample complexity for the problem of
low-rank tensor completion. Furthermore, we show that these bounds are nearly
minimax rate-optimal. We also provide promising numerical results for max-qnorm
constrained tensor completion, showing improved recovery results compared to
matricization and alternating least squares. |
---|---|
DOI: | 10.48550/arxiv.1711.04965 |