paper-with-me

Papers

Learning Linear Models Using Distributed Iterative Hessian Sketching

2021-12-08 · Han Wang, James Anderson

This work considers the problem of learning the Markov parameters of a linear system from observed data. Recent non-asymptotic system identification results have characterized the sample complexity of this problem in the single and multi-rollout setting. In both instances, the number of samples required in order to obtain acceptable estimates can produce optimization problems with an intractably large number of decision variables for a second-order algorithm. We show that a randomized and distributed Newton algorithm based on Hessian-sketching can produce $\epsilon$-optimal solutions and converges geometrically. Moreover, the algorithm is trivially parallelizable. Our results hold for a variety of sketching matrices and we illustrate the theory with numerical examples.

📄 PDF Abstract BibTeX arXiv:2112.04101

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Near-Optimal Private Linear Regression via Iterative Hessian Mixing

2026-01-12 · Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett 외 arxiv

We study differentially private ordinary least squares (DP-OLS) with bounded data $(X,Y)$ via sketching-based mechanisms. While Gaussian sketching approaches have been explored for DP-OLS \citep{sheffet2017differentially…

Learning-Augmented Sketches for Hessians

2021-02-24 · Yi Li, Honghao Lin, David P. Woodruff

Sketching is a dimensionality reduction technique where one compresses a matrix by linear combinations that are chosen at random. A line of work has shown how to sketch the Hessian to speed up each iteration in a second …

Dimensionality ReductionSecond-order methods

An Investigation of Newton-Sketch and Subsampled Newton Methods

2017-05-17 · Albert S. Berahas, Raghu Bollapragada, Jorge Nocedal

Sketching, a dimensionality reduction technique, has received much attention in the statistics community. In this paper, we study sketching in the context of Newton's method for solving finite-sum optimization problems i…

Dimensionality Reduction

Adaptive Iterative Hessian Sketch via A-Optimal Subsampling

2019-02-20 · Aijun Zhang, Hengtao Zhang, Guosheng Yin

Iterative Hessian sketch (IHS) is an effective sketching method for modeling large-scale data. It was originally proposed by Pilanci and Wainwright (2016; JMLR) based on randomized sketching matrices. However, it is comp…

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