Optimization landscape of Tucker decomposition

DOI10.1007/s10107-020-01531-zzbMath1494.90084arXiv2006.16297OpenAlexW3034401198MaRDI QIDQ2144548

Abraham Frandsen, Rong Ge

Publication date: 14 June 2022

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.16297

zbMATH Keywords

local searchnon-convex optimizationtensor decompositionoptimization landscape

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Basic linear algebra (15A99)

Uses Software

• Jellyfish

Cites Work

• Unnamed Item
• Operator norm inequalities between tensor unfoldings on the partition lattice
• Handwritten digit classification using higher order singular value decomposition
• Parallel stochastic gradient algorithms for large-scale matrix completion
• Cubic regularization of Newton method and its global performance
• Analysis of individual differences in multidimensional scaling via an \(n\)-way generalization of ``Eckart-Young decomposition
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• A Newton–Grassmann Method for Computing the Best Multilinear Rank-$(r_1,$ $r_2,$ $r_3)$ Approximation of a Tensor
• A Multilinear Singular Value Decomposition
• On the Best Rank-1 and Rank-(R₁ ,R₂ ,. . .,R_N) Approximation of Higher-Order Tensors
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Perturbation bounds in connection with singular value decomposition
• Distributional and \(L^q\) norm inequalities for polynomials over convex bodies in \(\mathbb{R}^n\)

This page was built for publication: Optimization landscape of Tucker decomposition