Robust low-rank tensor regression via truncation and adaptive Huber loss

05/03/2022
by   Kangqiang Li, et al.
0

This paper investigates robust low-rank tensor regression with only finite (1+ϵ)-th moment noise based on the generalized tensor estimation framework proposed by Han et al. (2022). The theoretical result shows that when ϵ≥ 1, the robust estimator possesses the minimax optimal rate. While 1> ϵ>0, the rate is slower than the deviation bound of sub-Gaussian tails.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/26/2020

An Optimal Statistical and Computational Framework for Generalized Tensor Estimation

This paper describes a flexible framework for generalized low-rank tenso...
research
06/19/2015

Doubly Decomposing Nonparametric Tensor Regression

Nonparametric extension of tensor regression is proposed. Nonlinearity i...
research
10/31/2017

Tensor Regression Meets Gaussian Processes

Low-rank tensor regression, a new model class that learns high-order cor...
research
08/24/2022

Group SLOPE Penalized CP Low-Rank Tensor Regression

This article aims to seek a selection and estimation procedure for a cla...
research
03/08/2021

Low-Rank Tensor Regression for X-Ray Tomography

Tomographic imaging is useful for revealing the internal structure of a ...
research
07/11/2022

Optimal Clustering by Lloyd Algorithm for Low-Rank Mixture Model

This paper investigates the computational and statistical limits in clus...
research
11/09/2019

ISLET: Fast and Optimal Low-rank Tensor Regression via Importance Sketching

In this paper, we develop a novel procedure for low-rank tensor regressi...

Please sign up or login with your details

Forgot password? Click here to reset