paper-with-me

홈 › Papers

Structured Low-Rank Tensors for Generalized Linear Models

2023-08-05 · Batoul Taki, Anand D. Sarwate, Waheed U. Bajwa

Recent works have shown that imposing tensor structures on the coefficient tensor in regression problems can lead to more reliable parameter estimation and lower sample complexity compared to vector-based methods. This work investigates a new low-rank tensor model, called Low Separation Rank (LSR), in Generalized Linear Model (GLM) problems. The LSR model -- which generalizes the well-known Tucker and CANDECOMP/PARAFAC (CP) models, and is a special case of the Block Tensor Decomposition (BTD) model -- is imposed onto the coefficient tensor in the GLM model. This work proposes a block coordinate descent algorithm for parameter estimation in LSR-structured tensor GLMs. Most importantly, it derives a minimax lower bound on the error threshold on estimating the coefficient tensor in LSR tensor GLM problems. The minimax bound is proportional to the intrinsic degrees of freedom in the LSR tensor GLM problem, suggesting that its sample complexity may be significantly lower than that of vectorized GLMs. This result can also be specialised to lower bound the estimation error in CP and Tucker-structured GLMs. The derived bounds are comparable to tight bounds in the literature for Tucker linear regression, and the tightness of the minimax lower bound is further assessed numerically. Finally, numerical experiments on synthetic datasets demonstrate the efficacy of the proposed LSR tensor model for three regression types (linear, logistic and Poisson). Experiments on a collection of medical imaging datasets demonstrate the usefulness of the LSR model over other tensor models (Tucker and CP) on real, imbalanced data with limited available samples.

📄 PDF Abstract BibTeX arXiv:2308.02922

Code (0)

등록된 구현이 없습니다.

Tasks

parameter estimationregressionTensor Decomposition

Methods 이 논문이 사용한 방법론

GLM GLM is a bilingual (English and Chinese) pre-trained transformer-based language model that follow the traditional architecture of decoder-only autoregressive language…
TuckER TuckER

Similar Papers 제목 키워드 기반

Statistical Inference for Low-Rank Tensor Models

2025-01-27 · Ke Xu, Elynn Chen, Yuefeng Han

Statistical inference for tensors has emerged as a critical challenge in analyzing high-dimensional data in modern data science. This paper introduces a unified framework for inferring general and low-Tucker-rank linear …

regression

Using Low-rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing

2021-03-30 · Lianru Gao, Zhicheng Wang, Lina Zhuang, Haoyang Yu 외

Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain th…

An algorithm for online tensor prediction

2015-07-28 · John Pothier, Josh Girson, Shuchin Aeron

We present a new method for online prediction and learning of tensors ($N$-way arrays, $N >2$) from sequential measurements. We focus on the specific case of 3-D tensors and exploit a recently developed framework of stru…

Prediction

Multilinear Low-Rank Tensors on Graphs & Applications

2016-11-15 · Nauman Shahid, Francesco Grassi, Pierre Vandergheynst

We propose a new framework for the analysis of low-rank tensors which lies at the intersection of spectral graph theory and signal processing. As a first step, we present a new graph based low-rank decomposition which ap…

EEGElectroencephalogram (EEG)

Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting

2020-02-25 · Qiquan Shi, Jiaming Yin, Jiajun Cai, Andrzej Cichocki 외

This work proposes a novel approach for multiple time series forecasting. At first, multi-way delay embedding transform (MDT) is employed to represent time series as low-rank block Hankel tensors (BHT). Then, the higher-…

Time SeriesTime Series AnalysisTime Series Forecasting