中文
相关论文

相关论文: Convergence for adaptive resampling of random Four…

200 篇论文

Least-squares approximation is one of the most important methods for recovering an unknown function from data. While in many applications the data is fixed, in many others there is substantial freedom to choose where to sample. In this…

机器学习 · 统计学 2025-08-11 Ben Adcock

In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning…

机器学习 · 计算机科学 2025-05-01 Yaru Liu , Yiqi Gu , Michael K. Ng

We consider the least-squares regression problem and provide a detailed asymptotic analysis of the performance of averaged constant-step-size stochastic gradient descent (a.k.a. least-mean-squares). In the strongly-convex case, we provide…

机器学习 · 计算机科学 2014-12-02 Alexandre Défossez , Francis Bach

Subsampling is an efficient method to deal with massive data. In this paper, we investigate the optimal subsampling for linear quantile regression when the covariates are functions. The asymptotic distribution of the subsampling estimator…

数值分析 · 数学 2022-05-06 Qian Yan , Hanyu Li , Chengmei Niu

We study the problem of recovering an unknown compactly-supported multivariate function from samples of its Fourier transform that are acquired nonuniformly, i.e. not necessarily on a uniform Cartesian grid. Reconstruction problems of this…

数值分析 · 数学 2022-05-04 Ben Adcock , Milana Gataric , José Luis Romero

This paper considers the model problem of reconstructing an object from incomplete frequency samples. Consider a discrete-time signal $f \in \C^N$ and a randomly chosen set of frequencies $\Omega$ of mean size $\tau N$. Is it possible to…

数值分析 · 数学 2007-05-23 Emmanuel Candes , Justin Romberg , Terence Tao

A recursive least squares algorithm with variable rate forgetting (VRF) is derived by minimizing a quadratic cost function.Under persistent excitation and boundedness of the forgetting factor, the minimizer given by VRF is shown to converge…

最优化与控制 · 数学 2020-03-06 Adam L. Bruce , Ankit Goel , Dennis S. Bernstein

In this paper, we propose a stochastic optimization method that adaptively controls the sample size used in the computation of gradient approximations. Unlike other variance reduction techniques that either require additional storage or the…

最优化与控制 · 数学 2017-11-01 Raghu Bollapragada , Richard Byrd , Jorge Nocedal

Feature subsampling is a core component of random forests and other ensemble methods. While recent theory suggests that this randomization acts solely as a variance reduction mechanism analogous to ridge regularization, these results…

机器学习 · 统计学 2026-01-06 Xin Chen , Jason M. Klusowski , Yan Shuo Tan , Chang Yu

Approximations based on random Fourier features have recently emerged as an efficient and formally consistent methodology to design large-scale kernel machines. By expressing the kernel as a Fourier expansion, features are generated based…

计算机视觉与模式识别 · 计算机科学 2012-03-08 Eduard Gabriel Băzăvan , Fuxin Li , Cristian Sminchisescu

High-dimensional limit theorems have been shown useful to derive tuning rules for finding the optimal scaling in random-walk Metropolis algorithms. The assumptions under which weak convergence results are proved are however restrictive: the…

统计方法学 · 统计学 2022-02-16 Sebastian M Schmon , Philippe Gagnon

The convergence analysis for least-squares finite element methods led to various adaptive mesh-refinement strategies: Collective marking algorithms driven by the built-in a posteriori error estimator or an alternative explicit…

数值分析 · 数学 2023-09-18 Philipp Bringmann

In this paper we study the performance of image reconstruction methods from incomplete samples of the 2D discrete Fourier transform. Inspired by requirements in parallel MRI, we focus on a special sampling pattern with a small number of…

数值分析 · 数学 2025-10-22 Gerlind Plonka , Anahita Riahi

Recently it has been established that asymptotic incoherence can be used to facilitate subsampling, in order to optimize reconstruction quality, in a variety of continuous compressed sensing problems, and the coherence structure of certain…

信息论 · 计算机科学 2016-10-25 Alex Jones , Ben Adcock , Anders Hansen

Kernel methods give powerful, flexible, and theoretically grounded approaches to solving many problems in machine learning. The standard approach, however, requires pairwise evaluations of a kernel function, which can lead to scalability…

机器学习 · 计算机科学 2021-04-08 Danica J. Sutherland , Jeff Schneider

The motivation for this paper stems from the desire to develop an adaptive sampling method for solving constrained optimization problems in which the objective function is stochastic and the constraints are deterministic. The method…

最优化与控制 · 数学 2021-01-01 Yuchen Xie , Raghu Bollapragada , Richard Byrd , Jorge Nocedal

In this work, we investigate data fitting problems with random noises. A randomized progressive iterative regularization method is proposed. It works well for large-scale matrix computations and converges in expectation to the least-squares…

数值分析 · 数学 2025-06-05 Dakang Cen , Wenlong Zhang , Junbin Zhong

Machine learning applied to computer vision and signal processing is achieving results comparable to the human brain on specific tasks due to the great improvements brought by the deep neural networks (DNN). The majority of state-of-the-art…

计算机视觉与模式识别 · 计算机科学 2020-06-30 José Augusto Stuchi , Levy Boccato , Romis Attux

We study the fundamental problem of selecting optimal features for model construction. This problem is computationally challenging on large datasets, even with the use of greedy algorithm variants. To address this challenge, we extend the…

Recently, it has been shown that incoherence is an unrealistic assumption for compressed sensing when applied to many inverse problems. Instead, the key property that permits efficient recovery in such problems is so-called local…

信息论 · 计算机科学 2015-07-09 Alex D. Jones , Ben Adcock , Anders C. Hansen