paper-with-me

홈 › Papers

A Minimax Lower Bound for Low-Rank Matrix-Variate Logistic Regression

2021-05-31 · Batoul Taki, Mohsen Ghassemi, Anand D. Sarwate, Waheed U. Bajwa

This paper considers the problem of matrix-variate logistic regression. It derives the fundamental error threshold on estimating low-rank coefficient matrices in the logistic regression problem by obtaining a lower bound on the minimax risk. The bound depends explicitly on the dimension and distribution of the covariates, the rank and energy of the coefficient matrix, and the number of samples. The resulting bound is proportional to the intrinsic degrees of freedom in the problem, which suggests the sample complexity of the low-rank matrix logistic regression problem can be lower than that for vectorized logistic regression. The proof techniques utilized in this work also set the stage for development of minimax lower bounds for tensor-variate logistic regression problems.

📄 PDF Abstract BibTeX arXiv:2105.14673

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

Similar Papers 제목 키워드 기반

Towards Optimal Estimation of Bivariate Isotonic Matrices with Unknown Permutations

2018-06-25 · Cheng Mao, Ashwin Pananjady, Martin J. Wainwright

Many applications, including rank aggregation, crowd-labeling, and graphon estimation, can be modeled in terms of a bivariate isotonic matrix with unknown permutations acting on its rows and/or columns. We consider the p…

Graphon Estimation

Optimal Schatten-q and Ky-Fan-k Norm Rate of Low Rank Matrix Estimation

2014-03-25 · Dong Xia

In this paper, we consider low rank matrix estimation using either matrix-version Dantzig Selector $\hat{A}_{\lambda}^d$ or matrix-version LASSO estimator $\hat{A}_{\lambda}^L$. We consider sub-Gaussian measurements, $i.…

Optimal Estimation and Computational Limit of Low-rank Gaussian Mixtures

2022-01-22 · Zhongyuan Lyu, Dong Xia

Structural matrix-variate observations routinely arise in diverse fields such as multi-layer network analysis and brain image clustering. While data of this type have been extensively investigated with fruitful outcomes …

Image Clustering

On the Optimality of Nuclear-norm-based Matrix Completion for Problems with Smooth Non-linear Structure

2021-05-05 · Yunhua Xiang, Tianyu Zhang, Xu Wang, Ali Shojaie 외

Originally developed for imputing missing entries in low rank, or approximately low rank matrices, matrix completion has proven widely effective in many problems where there is no reason to assume low-dimensional linear …

Matrix Completion

Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices

2019-12-23 · Jaouad Mourtada

We consider random-design linear prediction and related questions on the lower tail of random matrices. It is known that, under boundedness constraints, the minimax risk is of order $d/n$ in dimension $d$ with $n$ sample…

valid