paper-with-me

홈 › Papers

Online Covariance Matrix Estimation in Sketched Newton Methods

2025-02-10 · Wei Kuang, Mihai Anitescu, Sen Na

Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly standing out for their efficiency and robustness. In this paper, we study an online sketched Newton method that leverages a randomized sketching technique to perform an approximate Newton step in each iteration, thereby eliminating the computational bottleneck of second-order methods. While existing studies have established the asymptotic normality of sketched Newton methods, a consistent estimator of the limiting covariance matrix remains an open problem. We propose a fully online covariance matrix estimator that is constructed entirely from the Newton iterates and requires no matrix factorization. Compared to covariance estimators for first-order online methods, our estimator for second-order methods is batch-free. We establish the consistency and convergence rate of our estimator, and coupled with asymptotic normality results, we can then perform online statistical inference for the model parameters based on sketched Newton methods. We also discuss the extension of our estimator to constrained problems, and demonstrate its superior performance on regression problems as well as benchmark problems in the CUTEst set.

📄 PDF Abstract BibTeX arXiv:2502.07114

Code (1)

weikuang97/SketchedNT-Inf 공식 구현

Tasks

parameter estimationSecond-order methods

Similar Papers 제목 키워드 기반

Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming

2022-05-27 · Sen Na, Michael W. Mahoney

We consider online statistical inference of constrained stochastic nonlinear optimization problems. We apply the Stochastic Sequential Quadratic Programming (StoSQP) method to solve these problems, which can be regarded …

Second-order methodsStochastic Optimization

Inference of Online Newton Methods with Nesterov's Accelerated Sketching

2026-04-25 · Haoxuan Wang, Xinchen Du, Sen Na arxiv

Reliable decision-making with streaming data requires principled uncertainty quantification of online methods. While first-order methods enable efficient iterate updates, their inference procedures still require updating…

OverSketched Newton: Fast Convex Optimization for Serverless Systems

2019-03-21 · Vipul Gupta, Swanand Kadhe, Thomas Courtade, Michael W. Mahoney 외

Motivated by recent developments in serverless systems for large-scale computation as well as improvements in scalable randomized matrix algorithms, we develop OverSketched Newton, a randomized Hessian-based optimization…

Distributed Optimization

Efficient Second Order Online Learning by Sketching

2016-02-06 · NeurIPS 2016 12 · Haipeng Luo, Alekh Agarwal, Nicolo Cesa-Bianchi, John Langford

We propose Sketched Online Newton (SON), an online second order learning algorithm that enjoys substantially improved regret guarantees for ill-conditioned data. SON is an enhanced version of the Online Newton Step, whic…

Online Statistical Inference of Constrained Stochastic Optimization via Random Scaling

2025-05-23 · Xinchen Du, Wanrong Zhu, Wei Biao Wu, Sen Na

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…

Stochastic Optimization