中文
相关论文

相关论文: Inference in Randomized Least Squares and PCA via …

200 篇论文

Random projections or sketching are widely used in many algorithmic and learning contexts. Here we study the performance of iterative Hessian sketch for least-squares problems. By leveraging and extending recent results from random matrix…

最优化与控制 · 数学 2020-10-26 Jonathan Lacotte , Sifan Liu , Edgar Dobriban , Mert Pilanci

We consider a least squares regression problem where the data has been generated from a linear model, and we are interested to learn the unknown regression parameters. We consider "sketch-and-solve" methods that randomly project the data…

统计理论 · 数学 2019-10-08 Edgar Dobriban , Sifan Liu

Randomized algorithms, such as randomized sketching or stochastic optimization, are a promising approach to ease the computational burden in analyzing large datasets. However, randomized algorithms also produce non-deterministic outputs,…

统计方法学 · 统计学 2025-05-13 Zhixiang Zhang , Sokbae Lee , Edgar Dobriban

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…

统计方法学 · 统计学 2019-04-04 Daniel Ahfock , William J. Astle , Sylvia Richardson

We propose a new randomized algorithm for solving L2-regularized least-squares problems based on sketching. We consider two of the most popular random embeddings, namely, Gaussian embeddings and the Subsampled Randomized Hadamard Transform…

机器学习 · 计算机科学 2020-10-26 Jonathan Lacotte , Mert Pilanci

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 $(X, Y) \in \mathbb{R}^{n \times p} \times \mathbb{R}^n$,…

机器学习 · 统计学 2015-08-26 Garvesh Raskutti , Michael Mahoney

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…

机器学习 · 统计学 2015-05-26 Garvesh Raskutti , Michael Mahoney

We investigate iterative methods with randomized preconditioners for solving overdetermined least-squares problems, where the preconditioners are based on a random embedding of the data matrix. We consider two distinct approaches: the…

数值分析 · 数学 2021-04-15 Jonathan Lacotte , Mert Pilanci

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…

统计方法学 · 统计学 2023-06-07 R. P. Browne , J. L. Andrews

We provide an exact analysis of a class of randomized algorithms for solving overdetermined least-squares problems. We consider first-order methods, where the gradients are pre-conditioned by an approximation of the Hessian, based on a…

最优化与控制 · 数学 2020-02-27 Jonathan Lacotte , Mert Pilanci

We propose a novel randomized framework for the estimation problem of large-scale linear statistical models, namely Sequential Least-Squares Estimators with Fast Randomized Sketching (SLSE-FRS), which integrates Sketch-and-Solve and…

机器学习 · 统计学 2025-09-09 Guan-Yu Chen , Xi Yang

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…

机器学习 · 统计学 2022-06-23 Sokbae Lee , Serena Ng

Matrix sketching is a powerful tool for reducing the size of large data matrices. Yet there are fundamental limitations to this size reduction when we want to recover an accurate estimator for a task such as least square regression. We show…

数据结构与算法 · 计算机科学 2024-05-10 Sachin Garg , Kevin Tan , Michał Dereziński

Constrained stochastic nonlinear optimization problems have attracted significant attention for their ability to model complex real-world scenarios in physics, economics, and biology. As datasets continue to grow, online inference methods…

机器学习 · 统计学 2025-05-27 Xinchen Du , Wanrong Zhu , Wei Biao Wu , Sen Na

In our "big data" age, the size and complexity of data is steadily increasing. Methods for dimension reduction are ever more popular and useful. Two distinct types of dimension reduction are "data-oblivious" methods such as random…

统计理论 · 数学 2021-03-30 Fan Yang , Sifan Liu , Edgar Dobriban , David P. Woodruff

We study randomized sketching methods for approximately solving least-squares problem with a general convex constraint. The quality of a least-squares approximation can be assessed in different ways: either in terms of the value of the…

最优化与控制 · 数学 2014-11-04 Mert Pilanci , Martin J. Wainwright

A methodology for using random sketching in the context of model order reduction for high-dimensional parameter-dependent systems of equations was introduced in [Balabanov and Nouy 2019, Part I]. Following this framework, we here construct…

数值分析 · 数学 2022-03-25 Oleg Balabanov , Anthony Nouy

Subsampled Randomized Hadamard Transform (SRHT), a popular random projection method that can efficiently project a $d$-dimensional data into $r$-dimensional space ($r \ll d$) in $O(dlog(d))$ time, has been widely used to address the…

机器学习 · 计算机科学 2020-10-07 Zijian Lei , Liang Lan

A substantial body of work in machine learning (ML) and randomized numerical linear algebra (RandNLA) has exploited various sorts of random sketching methodologies, including random sampling and random projection, with much of the analysis…

数值分析 · 数学 2026-03-04 Chengmei Niu , Zhenyu Liao , Zenan Ling , Michael W. Mahoney

We consider distributed optimization methods for problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We leverage randomized sketches for reducing the problem dimensions as well as…

最优化与控制 · 数学 2022-03-21 Burak Bartan , Mert Pilanci
‹ 上一页 1 2 3 10 下一页 ›