Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization
From MaRDI portal
Abstract: We investigate a generalized framework to estimate a latent low-rank plus sparse tensor, where the low-rank tensor often captures the multi-way principal components and the sparse tensor accounts for potential model mis-specifications or heterogeneous signals that are unexplainable by the low-rank part. The framework is flexible covering both linear and non-linear models, and can easily handle continuous or categorical variables. We propose a fast algorithm by integrating the Riemannian gradient descent and a novel gradient pruning procedure. Under suitable conditions, the algorithm converges linearly and can simultaneously estimate both the low-rank and sparse tensors. The statistical error bounds of final estimates are established in terms of the gradient of loss function. The error bounds are generally sharp under specific statistical models, e.g., the robust tensor PCA and the community detection in hypergraph networks with outlier vertices. Moreover, our method achieves non-trivial error bounds for heavy-tailed tensor PCA whenever the noise has a finite moment. We apply our method to analyze the international trade flow dataset and the statistician hypergraph co-authorship network, both yielding new and interesting findings.
Cites work
- 1-bit matrix completion
- An optimal statistical and computational framework for generalized tensor estimation
- Bridging convex and nonconvex optimization in robust PCA: noise, outliers and missing data
- Coauthorship and citation networks for statisticians
- Common and individual structure of brain networks
- Community detection on mixture multilayer networks via regularized tensor decomposition
- Convex regularization for high-dimensional multiresponse tensor regression
- Covariate-adjusted tensor classification in high dimensions
- Dynamic tensor clustering
- Fast community detection by SCORE
- High-dimensional probability. An introduction with applications in data science
- Incoherent Tensor Norms and Their Applications in Higher Order Tensor Completion
- Inference for low-rank tensors -- no need to debias
- ISLET: fast and optimal low-rank tensor regression via importance sketching
- Learning from binary multiway data: probabilistic tensor decomposition and its statistical optimality
- Low-rank tensor completion by Riemannian optimization
- Main effects and interactions in mixed and incomplete data frames
- Multilayer tensor factorization with applications to recommender systems
- Non-convex projected gradient descent for generalized low-rank tensor regression
- Normal approximation and confidence region of singular subspaces
- On polynomial time methods for exact low-rank tensor completion
- Provable sparse tensor decomposition
- Robust principal component analysis?
- Sparse and Low-Rank Tensor Estimation via Cubic Sketchings
- Spectral and matrix factorization methods for consistent community detection in multi-layer networks
- Spectral clustering in the dynamic stochastic block model
- Spectral norm of products of random and deterministic matrices
- Statistically optimal and computationally efficient low rank tensor completion from noisy entries
- Tensor clustering with planted structures: statistical optimality and computational limits
- Tensor Decompositions and Applications
- Tensor decompositions for learning latent variable models
- Tensor Regression with Applications in Neuroimaging Data Analysis
- Tensor SVD: Statistical and Computational Limits
- The Geometry of Algorithms with Orthogonality Constraints
- The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising
Cited in
(14)- Sparse random tensors: concentration, regularization and applications
- A Riemannian Framework for Low-Rank Structured Elliptical Models
- Latent Space Model for Higher-Order Networks and Generalized Tensor Decomposition
- Robust tensor CUR decompositions: rapid low-Tucker-rank tensor recovery with sparse corruptions
- Robust Low-Rank Tensor Decomposition with the L 2 Criterion
- Optimal clustering by Lloyd's algorithm for low-rank mixture model
- Structured matrix learning under arbitrary entrywise dependence and estimation of Markov transition kernel
- Efficient Estimation for Longitudinal Networks via Adaptive Merging
- Computationally efficient and statistically optimal robust high-dimensional linear regression
- Robust tensor completion from uniformly dithered one-bit observations
- Tensor-on-tensor regression: Riemannian optimization, over-parameterization, statistical-computational gap and their interplay
- Conformalized Tensor Completion with Riemannian Optimization
- Online tensor learning: computational and statistical trade-offs, adaptivity and optimal regret
- Statistical inference in tensor completion: optimal uncertainty quantification and statistical-to-computational gaps
This page was built for publication: Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6144773)
