Experimental observation on a low-rank tensor model for eigenvalue problems
Machine Learning
2023-02-02 v1 Computational Physics
Abstract
Here we utilize a low-rank tensor model (LTM) as a function approximator, combined with the gradient descent method, to solve eigenvalue problems including the Laplacian operator and the harmonic oscillator. Experimental results show the superiority of the polynomial-based low-rank tensor model (PLTM) compared to the tensor neural network (TNN). We also test such low-rank architectures for the classification problem on the MNIST dataset.
Cite
@article{arxiv.2302.00538,
title = {Experimental observation on a low-rank tensor model for eigenvalue problems},
author = {Jun Hu and Pengzhan Jin},
journal= {arXiv preprint arXiv:2302.00538},
year = {2023}
}