An Optimal Statistical and Computational Framework for Generalized Tensor Estimation

by   Rungang Han, et al.

This paper describes a flexible framework for generalized low-rank tensor estimation problems that includes many important instances arising from applications in computational imaging, genomics, and network analysis. The proposed estimator consists of finding a low-rank tensor fit to the data under generalized parametric models. To overcome the difficulty of non-convexity in these problems, we introduce a unified approach of projected gradient descent that adapts to the underlying low-rank structure. Under mild conditions on the loss function, we establish both an upper bound on statistical error and the linear rate of computational convergence through a general deterministic analysis. Then we further consider a suite of generalized tensor estimation problems, including sub-Gaussian tensor denoising, tensor regression, and Poisson and binomial tensor PCA. We prove that the proposed algorithm achieves the minimax optimal rate of convergence in estimation error. Finally, we demonstrate the superiority of the proposed framework via extensive experiments on both simulated and real data.



There are no comments yet.


page 30


Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence

In this paper, we consider the estimation of a low Tucker rank tensor fr...

Generalized Low-rank plus Sparse Tensor Estimation by Fast Riemannian Optimization

We investigate a generalized framework to estimate a latent low-rank plu...

Generalized linear models with low rank effects for network data

Networks are a useful representation for data on connections between uni...

Sparse and Low-rank Tensor Estimation via Cubic Sketchings

In this paper, we propose a general framework for sparse and low-rank te...

Inference for Low-rank Tensors – No Need to Debias

In this paper, we consider the statistical inference for several low-ran...

Tensor Regression Using Low-rank and Sparse Tucker Decompositions

This paper studies a tensor-structured linear regression model with a sc...

Weighted Tensor Completion for Time-Series Causal Inference

Marginal Structural Models (MSM) Robins, 2000 are the most popular model...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.