DeepAI AI Chat
Log In Sign Up

STARK: Structured Dictionary Learning Through Rank-one Tensor Recovery

by   Mohsen Ghassemi, et al.
Rutgers University

In recent years, a class of dictionaries have been proposed for multidimensional (tensor) data representation that exploit the structure of tensor data by imposing a Kronecker structure on the dictionary underlying the data. In this work, a novel algorithm called "STARK" is provided to learn Kronecker structured dictionaries that can represent tensors of any order. By establishing that the Kronecker product of any number of matrices can be rearranged to form a rank-1 tensor, we show that Kronecker structure can be enforced on the dictionary by solving a rank-1 tensor recovery problem. Because rank-1 tensor recovery is a challenging nonconvex problem, we resort to solving a convex relaxation of this problem. Empirical experiments on synthetic and real data show promising results for our proposed algorithm.


page 1

page 2

page 3

page 4


Identifiability of Kronecker-structured Dictionaries for Tensor Data

This paper derives sufficient conditions for reliable recovery of coordi...

Learning Mixtures of Separable Dictionaries for Tensor Data: Analysis and Algorithms

This work addresses the problem of learning sparse representations of te...

Non-negative Tensor Patch Dictionary Approaches for Image Compression and Deblurring Applications

In recent work (Soltani, Kilmer, Hansen, BIT 2016), an algorithm for non...

Stochastic Iterative Hard Thresholding for Low-Tucker-Rank Tensor Recovery

Low-rank tensor recovery problems have been widely studied in many appli...

Online Multilinear Dictionary Learning for Sequential Compressive Sensing

A method for online tensor dictionary learning is proposed. With the ass...

Automating Personnel Rostering by Learning Constraints Using Tensors

Many problems in operations research require that constraints be specifi...

Minimax Lower Bounds for Kronecker-Structured Dictionary Learning

Dictionary learning is the problem of estimating the collection of atomi...