Optimization Landscape of Tucker Decomposition
Machine Learning
2020-07-01 v1 Data Structures and Algorithms
Optimization and Control
Machine Learning
Abstract
Tucker decomposition is a popular technique for many data analysis and machine learning applications. Finding a Tucker decomposition is a nonconvex optimization problem. As the scale of the problems increases, local search algorithms such as stochastic gradient descent have become popular in practice. In this paper, we characterize the optimization landscape of the Tucker decomposition problem. In particular, we show that if the tensor has an exact Tucker decomposition, for a standard nonconvex objective of Tucker decomposition, all local minima are also globally optimal. We also give a local search algorithm that can find an approximate local (and global) optimal solution in polynomial time.
Cite
@article{arxiv.2006.16297,
title = {Optimization Landscape of Tucker Decomposition},
author = {Abraham Frandsen and Rong Ge},
journal= {arXiv preprint arXiv:2006.16297},
year = {2020}
}