DeepAI AI Chat
Log In Sign Up

Optimal Low-Rank Tensor Recovery from Separable Measurements: Four Contractions Suffice

by   Parikshit Shah, et al.
The University of Texas at Austin

Tensors play a central role in many modern machine learning and signal processing applications. In such applications, the target tensor is usually of low rank, i.e., can be expressed as a sum of a small number of rank one tensors. This motivates us to consider the problem of low rank tensor recovery from a class of linear measurements called separable measurements. As specific examples, we focus on two distinct types of separable measurement mechanisms (a) Random projections, where each measurement corresponds to an inner product of the tensor with a suitable random tensor, and (b) the completion problem where measurements constitute revelation of a random set of entries. We present a computationally efficient algorithm, with rigorous and order-optimal sample complexity results (upto logarithmic factors) for tensor recovery. Our method is based on reduction to matrix completion sub-problems and adaptation of Leurgans' method for tensor decomposition. We extend the methodology and sample complexity results to higher order tensors, and experimentally validate our theoretical results.


page 29

page 30


Low Rank Triple Decomposition and Tensor Recovery

A simple approach for matrix completion and recovery is via low rank mat...

Cross: Efficient Low-rank Tensor Completion

The completion of tensors, or high-order arrays, attracts significant at...

Learning tensors from partial binary measurements

In this paper we generalize the 1-bit matrix completion problem to highe...

Learning Mixtures of Discrete Product Distributions using Spectral Decompositions

We study the problem of learning a distribution from samples, when the u...

Tensor Recovery from Noisy and Multi-Level Quantized Measurements

Higher-order tensors can represent scores in a rating system, frames in ...

Convex recovery of tensors using nuclear norm penalization

The subdifferential of convex functions of the singular spectrum of real...

Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements

Tensors, which provide a powerful and flexible model for representing mu...