Accelerated doubly stochastic gradient descent for tensor CP decomposition

DOI10.1007/s10957-023-02193-5zbMath1515.65110MaRDI QIDQ6161551

Unnamed Author, Chunfeng Cui, Deren Han

Publication date: 27 June 2023

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

zbMATH Keywords

nonconvex optimizationvariance reductionmomentum accelerationdoubly stochastic gradient descenttensor CANDECOMP/PARAFAC decomposition

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Multilinear algebra, tensor calculus (15A69) Numerical linear algebra (65F99)

Related Items

A block-randomized stochastic method with importance sampling for CP tensor decomposition, Provable stochastic algorithm for large-scale fully-connected tensor network decomposition

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tensor Decompositions and Applications
• Ergodic convergence to a zero of the sum of monotone operators in Hilbert space
• First-order and stochastic optimization methods for machine learning
• Analysis of individual differences in multidimensional scaling via an \(n\)-way generalization of ``Eckart-Young decomposition
• Momentum-based variance-reduced proximal stochastic gradient method for composite nonconvex stochastic optimization
• Randomized Alternating Least Squares for Canonical Tensor Decompositions: Application to A PDE With Random Data
• Optimization-Based Algorithms for Tensor Decompositions: Canonical Polyadic Decomposition, Decomposition in Rank-$(L_r,L_r,1)$ Terms, and a New Generalization
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Variational Analysis
• Tensor Decomposition for Signal Processing and Machine Learning
• Optimization Methods for Large-Scale Machine Learning
• A Practical Randomized CP Tensor Decomposition
• Accelerated Optimization for Machine Learning
• Stochastic Gradients for Large-Scale Tensor Decomposition
• Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization
• Generalized Canonical Polyadic Tensor Decomposition
• Tensor Rank and the Ill-Posedness of the Best Low-Rank Approximation Problem
• Tensor Analysis
• Some methods of speeding up the convergence of iteration methods
• A Stochastic Approximation Method
• Lower bounds for non-convex stochastic optimization