Tensor LISTA: Differentiable sparse representation learning for multi-dimensional tensor

The existing algorithms for sparse coding, which aim to seek sparse representation for given multi-dimensional signal, suffer from two main defects. Vector-based algorithms, e.g., LISTA, couldn’t handle the signal in tensor form well. On the other hand, tensor-based algorithms are not learnable yet,...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 463; pp. 554 - 565
Main Authors: Zhao, Qi, Liu, Guangcan, Liu, Qingshan
Format: Journal Article
Language:English
Published: Elsevier B.V 06.11.2021
Subjects:
Differentiable programming
Sparse coding
Tensor representation
Sparse coding
Tensor representation
Differentiable programming
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The existing algorithms for sparse coding, which aim to seek sparse representation for given multi-dimensional signal, suffer from two main defects. Vector-based algorithms, e.g., LISTA, couldn’t handle the signal in tensor form well. On the other hand, tensor-based algorithms are not learnable yet, leading to high computational cost. Towards this dilemma, we propose Tensor LISTA (TLISTA) bA to a multi-dimensional tensor-based model. Benefiting from tensor representation and differentiable programming, TLISTA achieves rapid inference speed and acquires more valuable representation for the data primarily organized in tensor form. Theoretical analysis about the convergence of TLISTA is then introduced, showing that TLISTA can attain the linear convergence rate. Extensive experiments confirm the effectiveness and efficiency of TLISTA for tensor sparse coding.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2021.08.024