English
Related papers

Related papers: Sparse sketches with small inversion bias

200 papers

We revisit the well-studied problem of approximating a matrix product, $\mathbf{A}^T\mathbf{B}$, based on small space sketches $\mathcal{S}(\mathbf{A})$ and $\mathcal{S}(\mathbf{B})$ of $\mathbf{A} \in \R^{n \times d}$ and $\mathbf{B}\in…

Data Structures and Algorithms · Computer Science 2025-01-30 Majid Daliri , Juliana Freire , Danrong Li , Christopher Musco

The debiased estimator is a crucial tool in statistical inference for high-dimensional model parameters. However, constructing such an estimator involves estimating the high-dimensional inverse Hessian matrix, incurring significant…

Machine Learning · Statistics 2023-12-18 Jiyuan Tu , Weidong Liu , Xiaojun Mao , Mingyue Xu

We develop a method for estimating well-conditioned and sparse covariance and inverse covariance matrices from a sample of vectors drawn from a sub-gaussian distribution in high dimensional setting. The proposed estimators are obtained by…

Statistics Theory · Mathematics 2016-11-21 Ashwini Maurya

Given $n$ i.i.d. observations of a random vector $(X,Z)$, where $X$ is a high-dimensional vector and $Z$ is a low-dimensional index variable, we study the problem of estimating the conditional inverse covariance matrix $\Omega(z) =…

Machine Learning · Statistics 2014-12-25 Jialei Wang , Mladen Kolar

In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. However, the local estimates on each machine are typically biased, relative to…

Machine Learning · Computer Science 2020-07-06 Michał Dereziński , Burak Bartan , Mert Pilanci , Michael W. Mahoney

Random sampling is a fundamental tool in modern machine learning and numerical linear algebra for reducing the computational cost of large-scale matrix problems. Existing analyses, however, rely primarily on subspace embedding guarantees,…

Numerical Analysis · Mathematics 2026-05-26 Chengmei Niu , Sachin Garg , Michał Dereziński , Zhenyu Liao

The L1-regularized Gaussian maximum likelihood estimator (MLE) has been shown to have strong statistical guarantees in recovering a sparse inverse covariance matrix, or alternatively the underlying graph structure of a Gaussian Markov…

Machine Learning · Computer Science 2013-06-14 Cho-Jui Hsieh , Matyas A. Sustik , Inderjit S. Dhillon , Pradeep Ravikumar

Sketching is a probabilistic data compression technique that has been largely developed in the computer science community. Numerical operations on big datasets can be intolerably slow; sketching algorithms address this issue by generating a…

Methodology · Statistics 2019-04-04 Daniel Ahfock , William J. Astle , Sylvia Richardson

Researchers may perform regressions using a sketch of data of size $m$ instead of the full sample of size $n$ for a variety of reasons. This paper considers the case when the regression errors do not have constant variance and…

Machine Learning · Statistics 2022-06-23 Sokbae Lee , Serena Ng

Constrained least squares problems arise in many applications. Their memory and computation costs are expensive in practice involving high-dimensional input data. We employ the so-called "sketching" strategy to project the least squares…

Optimization and Control · Mathematics 2021-09-07 Ke Chen , Ruhui Jin

This paper considers the problem of recovering an unknown sparse p\times p matrix X from an m\times m matrix Y=AXB^T, where A and B are known m \times p matrices with m << p. The main result shows that there exist constructions of the…

Information Theory · Computer Science 2013-03-27 Gautam Dasarathy , Parikshit Shah , Badri Narayan Bhaskar , Robert Nowak

Sketching algorithms use random projections to generate a smaller sketched data set, often for the purposes of modelling. Complete and partial sketch regression estimates can be constructed using information from only the sketched data set…

Methodology · Statistics 2023-06-07 R. P. Browne , J. L. Andrews

We introduce a new method for sparse principal component analysis, based on the aggregation of eigenvector information from carefully-selected axis-aligned random projections of the sample covariance matrix. Unlike most alternative…

Methodology · Statistics 2019-05-07 Milana Gataric , Tengyao Wang , Richard J. Samworth

We propose a new method of learning a sparse nonnegative-definite target matrix. Our primary example of the target matrix is the inverse of a population covariance or correlation matrix. The algorithm first estimates each column of the…

Statistics Theory · Mathematics 2013-10-15 Tingni Sun , Cun-Hui Zhang

We consider statistical as well as algorithmic aspects of solving large-scale least-squares (LS) problems using randomized sketching algorithms. For a LS problem with input data $(X, Y) \in \mathbb{R}^{n \times p} \times \mathbb{R}^n$,…

Machine Learning · Statistics 2015-08-26 Garvesh Raskutti , Michael Mahoney

We give a sketching-based iterative algorithm that computes a $1+\varepsilon$ approximate solution for the ridge regression problem $\min_x \|Ax-b\|_2^2 +\lambda\|x\|_2^2$ where $A \in R^{n \times d}$ with $d \ge n$. Our algorithm, for a…

Data Structures and Algorithms · Computer Science 2022-06-20 Praneeth Kacham , David P. Woodruff

In distributed systems, communication is a major concern due to issues such as its vulnerability or efficiency. In this paper, we are interested in estimating sparse inverse covariance matrices when samples are distributed into different…

Methodology · Statistics 2016-10-04 Jesús Arroyo , Elizabeth Hou

We consider statistical and algorithmic aspects of solving large-scale least-squares (LS) problems using randomized sketching algorithms. Prior results show that, from an \emph{algorithmic perspective}, when using sketching matrices…

Machine Learning · Statistics 2015-05-26 Garvesh Raskutti , Michael Mahoney

The paper proposes a new covariance estimator for large covariance matrices when the variables have a natural ordering. Using the Cholesky decomposition of the inverse, we impose a banded structure on the Cholesky factor, and select the…

Applications · Statistics 2008-12-18 Elizaveta Levina , Adam Rothman , Ji Zhu

High-dimensional sparse data present computational and statistical challenges for supervised learning. We propose compact linear sketches for reducing the dimensionality of the input, followed by a single layer neural network. We show that…

Machine Learning · Computer Science 2016-04-21 Amit Daniely , Nevena Lazic , Yoram Singer , Kunal Talwar