Convex regularization for high-dimensional multiresponse tensor regression
From MaRDI portal
Abstract: In this paper we present a general convex optimization approach for solving high-dimensional multiple response tensor regression problems under low-dimensional structural assumptions. We consider using convex and weakly decomposable regularizers assuming that the underlying tensor lies in an unknown low-dimensional subspace. Within our framework, we derive general risk bounds of the resulting estimate under fairly general dependence structure among covariates. Our framework leads to upper bounds in terms of two very simple quantities, the emph{Gaussian width} of a convex set in tensor space and the emph{intrinsic dimension} of the low-dimensional tensor subspace. To the best of our knowledge, this is the first general framework that applies to multiple response problems. These general bounds provide useful upper bounds on rates of convergence for a number of fundamental statistical models of interest including multi-response regression, vector auto-regressive models, low-rank tensor models and pairwise interaction models. Moreover, in many of these settings we prove that the resulting estimates are minimax optimal. We also provide a numerical study that both validates our theoretical guarantees and demonstrates the breadth of our framework.
Recommendations
- Regularized high dimension low tubal-rank tensor regression
- Learning with tensors: a framework based on convex optimization and spectral regularization
- Non-convex projected gradient descent for generalized low-rank tensor regression
- An optimal statistical and computational framework for generalized tensor estimation
- Fundamental barriers to high-dimensional regression with convex penalties
Cited in
(55)- Tensor-on-Tensor Regression
- Reshaped tensor nuclear norms for higher order tensor completion
- An optimal statistical and computational framework for generalized tensor estimation
- Fundamental barriers to high-dimensional regression with convex penalties
- Inference for low-rank tensors -- no need to debias
- A general framework for tensor screening through smoothing
- Regularized high dimension low tubal-rank tensor regression
- Learning with tensors: a framework based on convex optimization and spectral regularization
- High-dimensional constrained matrix regression problems
- L2RM: Low-Rank Linear Regression Models for High-Dimensional Matrix Responses
- Non-convex projected gradient descent for generalized low-rank tensor regression
- Sparse tensor additive regression
- Bayesian regression with undirected network predictors with an application to brain connectome data
- ISLET: fast and optimal low-rank tensor regression via importance sketching
- Tensor Regression Using Low-Rank and Sparse Tucker Decompositions
- Generalized Tensor Decomposition With Features on Multiple Modes
- A sharp blockwise tensor perturbation bound for orthogonal iteration
- Theoretical and experimental analyses of tensor-based regression and classification
- High-Dimensional Vector Autoregressive Time Series Modeling via Tensor Decomposition
- Estimation of Low Rank High-Dimensional Multivariate Linear Models for Multi-Response Data
- Multiple change points detection in high-dimensional multivariate regression
- The EAS approach for graphical selection consistency in vector autoregression models
- Statistical inference on the significance of rows and columns for matrix-valued data in an additive model
- LOCUS: a regularized blind source separation method with low-rank structure for investigating brain connectivity
- Correlation Tensor Decomposition and Its Application in Spatial Imaging Data
- A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering
- Parsimonious Tensor Discriminant Analysis
- Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization
- Bayesian Dynamic Tensor Regression
- High-dimensional low-rank tensor autoregressive time series modeling
- Low-rank matrix estimation via nonconvex optimization methods in multi-response errors-in-variables regression
- Optimality conditions for Tucker low-rank tensor optimization
- Statistical performance of quantile tensor regression with convex regularization
- An improved tensor regression model via location smoothing
- Low-rank tensor regression for selection of grouped variables
- Uniform recovery guarantees for quantized corrupted sensing using structured or generative priors
- Reduced-Rank Envelope Vector Autoregressive Model
- Multiple Tensor-on-Tensor Regression: An Approach for Modeling Processes With Heterogeneous Sources of Data
- Theoretical guarantees for low-rank compression of deep neural networks
- Projection pursuit Bayesian regression for symmetric matrix predictors
- Multi-Dimensional Domain Generalization with Low-Rank Structures
- Sample Efficient Nonparametric Regression via Low-Rank Regularization
- Statistical inference for tensor-based covariates in Cox regression modeling in integrated genome studies
- Broadcasted nonparametric tensor regression
- Tensor train regression with convex regularization
- Integrative tensor regression for stratified data with application to neuroimaging analysis
- CeCNN: copula-enhanced convolutional neural networks in joint prediction of refraction error and axial length based on ultra-widefield fundus images
- Fourth order random tensors and their applications in statistics
- Low-rank matrix recovery via nonconvex optimization methods with application to errors-in-variables matrix regression
- Tensor-on-tensor regression: Riemannian optimization, over-parameterization, statistical-computational gap and their interplay
- Tensor-on-vector regression with interactions with application to fMRI data
- Sparse higher-order partial least squares for simultaneous variable selection, dimension reduction and tensor denoising
- Partial Envelope and Reduced-Rank Partial Envelope Vector Autoregressive Models
- Conditional Probability Tensor Decompositions for Multivariate Categorical Response Regression
- Envelope Matrix Autoregressive Models
This page was built for publication: Convex regularization for high-dimensional multiresponse tensor regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2414097)
