Almost-lossless compression of a low-rank random tensor

10/08/2022

∙

In this work, we establish an asymptotic limit of almost-lossless compression of a random, finite alphabet tensor which admits a low-rank canonical polyadic decomposition.

READ FULL TEXT

Almost-lossless compression of a low-rank random tensor

One time is not enough: iterative tensor decomposition for neural network compression

The core consistency of a compressed tensor

Low-Rank Tensor Decomposition via Multiple Reshaping and Reordering Operations

Experimental observation on a low-rank tensor model for eigenvalue problems

Tensor Regression Networks with various Low-Rank Tensor Approximations

Optimizing Orthogonalized Tensor Deflation via Random Tensor Theory

Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization

Almost-lossless compression of a low-rank random tensor

Related Research

One time is not enough: iterative tensor decomposition for neural network compression

The core consistency of a compressed tensor

Low-Rank Tensor Decomposition via Multiple Reshaping and Reordering Operations

Experimental observation on a low-rank tensor model for eigenvalue problems

Tensor Regression Networks with various Low-Rank Tensor Approximations

Optimizing Orthogonalized Tensor Deflation via Random Tensor Theory

Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization