English
Related papers

Related papers: Sketched Ridge Regression: Optimization Perspectiv…

200 papers

The singular value decomposition (SVD) of large-scale matrices is a key tool in data analytics and scientific computing. The rapid growth in the size of matrices further increases the need for developing efficient large-scale SVD…

Numerical Analysis · Mathematics 2016-08-31 Ting-Li Chen , Dawei D. Chang , Su-Yun Huang , Hung Chen , Chienyao Lin , Weichung Wang

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 algorithm to solve…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-08-28 Vipul Gupta , Swanand Kadhe , Thomas Courtade , Michael W. Mahoney , Kannan Ramchandran

Stochastic gradient descent (SGD) provides a simple and efficient way to solve a broad range of machine learning problems. Here, we focus on distribution regression (DR), involving two stages of sampling: Firstly, we regress from…

Machine Learning · Statistics 2021-03-08 Nicole Mücke

Ridge regression is an indispensable tool in big data analysis. Yet its inherent bias poses a significant and longstanding challenge, compromising both statistical efficiency and scalability across various applications. To tackle this…

Econometrics · Economics 2024-07-25 Zhaoxing Gao , Ruey S. Tsay

We propose a novel limited-memory stochastic block BFGS update for incorporating enriched curvature information in stochastic approximation methods. In our method, the estimate of the inverse Hessian matrix that is maintained by it, is…

Optimization and Control · Mathematics 2016-04-01 Robert M. Gower , Donald Goldfarb , Peter Richtárik

In order to compute fast approximations to the singular value decompositions (SVD) of very large matrices, randomized sketching algorithms have become a leading approach. However, a key practical difficulty of sketching an SVD is that the…

Machine Learning · Statistics 2020-03-12 Miles E. Lopes , N. Benjamin Erichson , Michael W. Mahoney

Linear sketching and recovery of sparse vectors with randomly constructed sparse matrices has numerous applications in several areas, including compressive sensing, data stream computing, graph sketching, and combinatorial group testing.…

Numerical Analysis · Mathematics 2014-02-07 Bubacarr Bah , Luca Baldassarre , Volkan Cevher

In this paper, we propose {\it \underline{R}ecursive} {\it \underline{I}mportance} {\it \underline{S}ketching} algorithm for {\it \underline{R}ank} constrained least squares {\it \underline{O}ptimization} (RISRO). The key step of RISRO is…

Optimization and Control · Mathematics 2022-12-06 Yuetian Luo , Wen Huang , Xudong Li , Anru R. Zhang

Sketching-based preconditioners have been shown to accelerate the solution of dense least-squares problems with coefficient matrices having substantially more rows than columns. The cost of generating these preconditioners can be reduced by…

Numerical Analysis · Mathematics 2025-06-12 Erin Carson , Ieva Daužickaitė

Regularization is used to find a solution that both fits the data and is sufficiently smooth, and thereby is very effective for designing and refining learning algorithms. But the influence of its exponent remains poorly understood. In…

Machine Learning · Statistics 2016-12-15 Julien Audiffren , Hachem Kadri

Motivated by the randomized sketch to solve a variety of problems in scientific computation, we improve both the maximal weighted residual Kaczmarz method and the randomized block average Kaczmarz method using two new randomized sketch…

Numerical Analysis · Mathematics 2025-11-18 Haochen Jiang , Dongdong Liu , Xianping Wu , Xu Yang

Motivated by applications in optimization and machine learning, we consider stochastic quasi-Newton (SQN) methods for solving stochastic optimization problems. In the literature, the convergence analysis of these algorithms relies on strong…

Optimization and Control · Mathematics 2016-03-16 Farzad Yousefian , Angelia Nedić , Uday V. Shanbha

Projection-based iterative methods for solving large over-determined linear systems are well-known for their simplicity and computational efficiency. It is also known that the correct choice of a sketching procedure (i.e., preprocessing…

Numerical Analysis · Mathematics 2019-12-03 Elizaveta Rebrova , Deanna Needell

We consider an on-line least squares regression problem with optimal solution $\theta^*$ and Hessian matrix H, and study a time-average stochastic gradient descent estimator of $\theta^*$. For $k\ge2$, we provide an unbiased estimator of…

Machine Learning · Statistics 2025-11-18 Nabil Kahalé

We propose new approximate alternating projection methods, based on randomized sketching, for the low-rank nonnegative matrix approximation problem: find a low-rank approximation of a nonnegative matrix that is nonnegative, but whose…

Numerical Analysis · Mathematics 2023-04-25 Sergey A. Matveev , Stanislav Budzinskiy

The Dirac-Frenkel variational principle is a widely used building block for using nonlinear parametrizations in the context of model reduction and numerically solving partial differential equations; however, it typically leads to…

Numerical Analysis · Mathematics 2025-12-23 Yijun Dong , Paul Schwerdtner , Benjamin Peherstorfer

In this paper we discuss an application of Stochastic Approximation to statistical estimation of high-dimensional sparse parameters. The proposed solution reduces to resolving a penalized stochastic optimization problem on each stage of a…

Machine Learning · Statistics 2022-10-25 Sasila Ilandarideva , Yannis Bekri , Anatoli Juditsky , Vianney Perchet

The sketch-and-project, as a general archetypal algorithm for solving linear systems, unifies a variety of randomized iterative methods such as the randomized Kaczmarz and randomized coordinate descent. However, since it aims to find a…

Numerical Analysis · Mathematics 2022-05-04 Ziyang Yuan , Lu Zhang , Hongxia Wang , Hui Zhang

We develop a family of accelerated stochastic algorithms that minimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in particular linear least-squares regression,…

Machine Learning · Statistics 2015-06-25 Roy Frostig , Rong Ge , Sham M. Kakade , Aaron Sidford

The history of the seemingly simple problem of straight line fitting in the presence of both $x$ and $y$ errors has been fraught with misadventure, with statistically ad hoc and poorly tested methods abounding in the literature. The problem…

Methodology · Statistics 2023-11-15 Deaglan Bartlett , Harry Desmond