Theoretical Bounds for Noise Filtration using Low-Rank Tensor Approximations

Autor:	Petrov, Sergey, Zamarashkin, Nikolai
Rok vydání:	2023
Předmět:	Mathematics - Numerical Analysis
Druh dokumentu:	Working Paper
Popis:	Low-rank tensor approximation error bounds are proposed for the case of noisy input data that depend on low-rank representation type, rank and the dimensionality of the tensor. The bounds show that high-dimensional low-rank structured approximations provide superior noise-filtering properties compared to matrices with the same rank and total element count.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2312.02088 Zobrazit plný text záznamu View this record from Arxiv