Non-convex projected gradient descent for generalized low-rank tensor regression

zbMATH Open1483.62091arXiv1611.10349MaRDI QIDQ4633013FDOQ4633013

Authors: Han Chen, Garvesh Raskutti, Ming Yuan 

Publication date: 2 May 2019

Full work available at URL: https://arxiv.org/abs/1611.10349

Recommendations

• Nonconvex Low-Rank Tensor Completion from Noisy Data
• Gradient descent with non-convex constraints: local concavity determines convergence
• Convergence analysis of projected gradient descent for Schatten-\(p\) nonconvex matrix recovery
• An optimal statistical and computational framework for generalized tensor estimation
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity

zbMATH Keywords

high-dimensional regressionlow-ranknon-convex optimizationtensors

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05) Estimation in multivariate analysis (62H12) Generalized linear models (logistic models) (62J12) Multilinear algebra, tensor calculus (15A69)

Cites Work

• Regularized estimation in sparse high-dimensional time series models
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Statistics for high-dimensional data. Methods, theory and applications.
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers
• Title not available (Why is that?)
• Tensor Decompositions and Applications
• Convex Analysis
• Convex regularization for high-dimensional multiresponse tensor regression
• Local Rademacher complexities
• Tensor completion and low-\(n\)-rank tensor recovery via convex optimization
• The convex geometry of linear inverse problems
• Title not available (Why is that?)
• Regularized \(M\)-estimators with nonconvexity: statistical and algorithmic theory for local optima
• Upper bounds on product and multiplier empirical processes
• Tensor Algebra and Multidimensional Harmonic Retrieval in Signal Processing for MIMO Radar
• Tensor-Based Formulation and Nuclear Norm Regularization for Multienergy Computed Tomography

Cited In (23)

• Multivariate Temporal Point Process Regression
• Gradient-based optimization for regression in the functional tensor-train format
• ISLET: fast and optimal low-rank tensor regression via importance sketching
• Gradient descent with non-convex constraints: local concavity determines convergence
• Non-convex optimization for machine learning
• An optimal statistical and computational framework for generalized tensor estimation
• Inference for low-rank tensors -- no need to debias
• Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization
• Low-rank tensor regression for selection of grouped variables
• Title not available (Why is that?)
• Convex regularization for high-dimensional multiresponse tensor regression
• Tensor completion with noisy side information
• Low-rank matrix estimation via nonconvex optimization methods in multi-response errors-in-variables regression
• Optimality conditions for Tucker low-rank tensor optimization
• Title not available (Why is that?)
• Multiple Tensor-on-Tensor Regression: An Approach for Modeling Processes With Heterogeneous Sources of Data
• Nonconvex Low-Rank Tensor Completion from Noisy Data
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Tensor Regression Using Low-Rank and Sparse Tucker Decompositions
• Partially Observed Dynamic Tensor Response Regression
• Title not available (Why is that?)
• An improved tensor regression model via location smoothing
• Low-rank, Orthogonally Decomposable Tensor Regression With Application to Visual Stimulus Decoding of fMRI Data

This page was built for publication: Non-convex projected gradient descent for generalized low-rank tensor regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4633013)