Tensor Canonical Correlation Analysis With Convergence and Statistical Guarantees

DOI10.1080/10618600.2020.1856118OpenAlexW3110664783MaRDI QIDQ5066457

Mladen Kolar, Ruey S. Tsay, You-Lin Chen

Publication date: 29 March 2022

Published in: Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.05358

zbMATH Keywords

nonconvex optimizationcanonical correlation analysisdeflationtensor decompositionhigher-order power methodLojasiewicz's inequalities

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (1)

Provably training overparameterized neural network classifiers with non-convex constraints

Uses Software

• JADE

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tensor Decompositions and Applications
• Sparse Generalized Eigenvalue Problem: Optimal Statistical Rates via Truncated Rayleigh Flow
• Model selection and estimation in the matrix normal graphical model
• The multilinear normal distribution: introduction and some basic properties
• A survey of multilinear subspace learning for tensor data
• Class label versus sample label-based CCA
• Advanced intelligent computing theories and applications. With aspects of contemporary intelligent computing techniques. 4th international conference on intelligent computing, ICIC 2008 Shanghai, China, September 15--18, 2008. Proceedings
• Error bounds and convergence analysis of feasible descent methods: A general approach
• Convergence rate analysis for the higher order power method in best rank one approximations of tensors
• Convergence analysis of an SVD-based algorithm for the best rank-1 tensor approximation
• From error bounds to the complexity of first-order descent methods for convex functions
• Independent component analysis for tensor-valued data
• Factor models for matrix-valued high-dimensional time series
• Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
• Maximum likelihood estimation for the tensor normal distribution: Algorithm, minimum sample size, and empirical bias and dispersion
• Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm
• Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods
• A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion
• A new convergence proof for the higher-order power method and generalizations
• On Convergence of the Maximum Block Improvement Method
• Convergence Results for Projected Line-Search Methods on Varieties of Low-Rank Matrices Via Łojasiewicz Inequality
• JADE for Tensor-Valued Observations
• A Multilinear Singular Value Decomposition
• On the Best Rank-1 and Rank-(R₁ ,R₂ ,. . .,R_N) Approximation of Higher-Order Tensors
• On Estimation of Covariance Matrices With Kronecker Product Structure
• Scalable and Flexible Multiview MAX-VAR Canonical Correlation Analysis
• Sparse Matrix Graphical Models
• Canonical Correlation Analysis: An Overview with Application to Learning Methods
• Regularized Matrix Regression
• Constrained Factor Models for High-Dimensional Matrix-Variate Time Series
• Finding Low-Rank Solutions via Nonconvex Matrix Factorization, Efficiently and Provably
• Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
• Structured lasso for regression with matrix covariates
• Convergence of the Iterates of Descent Methods for Analytic Cost Functions
• RELATIONS BETWEEN TWO SETS OF VARIATES

This page was built for publication: Tensor Canonical Correlation Analysis With Convergence and Statistical Guarantees