Paper ID: 2504.00008 • Published Mar 25, 2025
Tensor Generalized Approximate Message Passing
Yinchuan Li, Guangchen Lan, Xiaodong Wang
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
We propose a tensor generalized approximate message passing (TeG-AMP)
algorithm for low-rank tensor inference, which can be used to solve tensor
completion and decomposition problems. We derive TeG-AMP algorithm as an
approximation of the sum-product belief propagation algorithm in high
dimensions where the central limit theorem and Taylor series approximations are
applicable. As TeG-AMP is developed based on a general TR decomposition model,
it can be directly applied to many low-rank tensor types. Moreover, our TeG-AMP
can be simplified based on the CP decomposition model and a tensor simplified
AMP is proposed for low CP-rank tensor inference problems. Experimental results
demonstrate that the proposed methods significantly improve recovery
performances since it takes full advantage of tensor structures.