Optimization Landscape of Tucker Decomposition

06/29/2020
by   Abraham Frandsen, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/18/2017

On the Optimization Landscape of Tensor Decompositions

Non-convex optimization with local search heuristics has been widely use...
research
10/25/2021

Faster Perturbed Stochastic Gradient Methods for Finding Local Minima

Escaping from saddle points and finding local minima is a central proble...
research
01/07/2022

Local and Global Convergence of General Burer-Monteiro Tensor Optimizations

Tensor optimization is crucial to massive machine learning and signal pr...
research
10/28/2016

Homotopy Analysis for Tensor PCA

Developing efficient and guaranteed nonconvex algorithms has been an imp...
research
06/03/2021

Linear regression with partially mismatched data: local search with theoretical guarantees

Linear regression is a fundamental modeling tool in statistics and relat...
research
11/08/2016

Recursive Decomposition for Nonconvex Optimization

Continuous optimization is an important problem in many areas of AI, inc...
research
07/14/2020

From Symmetry to Geometry: Tractable Nonconvex Problems

As science and engineering have become increasingly data-driven, the rol...

Please sign up or login with your details

Forgot password? Click here to reset