Stochastic Gradients for Large-Scale Tensor Decomposition

DOI10.1137/19M1266265zbMath1485.65054arXiv1906.01687OpenAlexW3096024647MaRDI QIDQ5037555

David Hong, Tamara G. Kolda

Publication date: 1 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.01687

zbMATH Keywords

stochastic optimizationstratified samplingtensor decompositionstochastic gradients

Mathematics Subject Classification ID

Multilinear algebra, tensor calculus (15A69) Numerical linear algebra (65F99) Probabilistic methods, stochastic differential equations (65C99)

Related Items (7)

Performance of the Low-Rank TT-SVD for Large Dense Tensors on Modern MultiCore CPUs ⋮ Practical Leverage-Based Sampling for Low-Rank Tensor Decomposition ⋮ A block-randomized stochastic method with importance sampling for CP tensor decomposition ⋮ Accelerated doubly stochastic gradient descent for tensor CP decomposition ⋮ Provable stochastic algorithm for large-scale fully-connected tensor network decomposition ⋮ An AO-ADMM Approach to Constraining PARAFAC2 on All Modes ⋮ Inertial accelerated SGD algorithms for solving large-scale lower-rank tensor CP decomposition problems

Uses Software

• TensorToolbox
• LBFGS-B
• Adam
• LowRankModels
• Pyglrm
• FROSTT
• SPLATT
• Genten

Cites Work

• Tensor Decompositions and Applications
• Asymptotic performance of PCA for high-dimensional heteroscedastic data
• Analysis of individual differences in multidimensional scaling via an \(n\)-way generalization of ``Eckart-Young decomposition
• Positive tensor factorization
• Completing Any Low-rank Matrix, Provably
• Generalized Low Rank Models
• Computational Advertising: Techniques for Targeting Relevant Ads
• A Scalable Generative Graph Model with Community Structure
• Randomized Algorithms for Matrices and Data
• Newton-based optimization for Kullback–Leibler nonnegative tensor factorizations
• Algorithm 862
• Efficient MATLAB Computations with Sparse and Factored Tensors
• Adaptive Algorithms to Track the PARAFAC Decomposition of a Third-Order Tensor
• Subspace Learning and Imputation for Streaming Big Data Matrices and Tensors
• A Practical Randomized CP Tensor Decomposition
• A Limited Memory Algorithm for Bound Constrained Optimization
• On Tensors, Sparsity, and Nonnegative Factorizations
• Generalized Canonical Polyadic Tensor Decomposition
• Software for Sparse Tensor Decomposition on Emerging Computing Architectures
• Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm

This page was built for publication: Stochastic Gradients for Large-Scale Tensor Decomposition