On the Convergence of Randomized Kaczmarz Algorithm in Hilbert Space

来源 :上海交通大学 | 被引量 : 0次 | 上传用户:clisav
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  Randomized Kaczmarz algorithm was designed for solving linear equation systems.Inspired by the recent development of the analysis,we give the convergence of randomized Kaczmarz algorithm in Hilbert space.The analysis is then applied to online learning algorithms with kernels,and functional linear regression.
其他文献
The spatial random-effects model is flexible in modeling spatial covariance functions,and is computationally efficient for spatial prediction via fixed rank kriging.However,the model depends on a clas
A closed-form estimator and its several robust versions for the integer-valued GARCH(1,1)model are proposed.These estimators are easy to implement and do not require the use of any numerical optimizat
Stochastic processes become more and more popular to model the mesoscopic biophysical dynamics,especially in single-cell biology.We proposed a fluctuating-rate model for the stochastic biochemical dyn
Human-associated microbial communities may have substantial impact on human health and disease.In each niche,there may be a high degree of competition and cooperation within the microbiome.High-throug
Nonignorable missing data occur frequently in longitudinal studies and can cause biased estimations.Refreshment samples which draw new subjects randomly in sub-sequent waves from the original populati
We use ordinary differential equations(ODE)to model the directional interaction,also called effective connectivity,among brain regions.In contrast to existing ODE models that focus on effective connec
We consider the problem of uncertainty assessment for low dimensional components in high dimensional models.Specifically,we propose a decorrelated score function to handle the impact of high dimension
The increased availability of massive datasets provides a unique opportunity to discover subtle patterns in their distributions,but also imposes overwhelming computational challenges.To fully utilize
会议
We propose an empirical likelihood(EL)method for constructing confidence intervals for population parameters defined by estimation equations(EEs)with data from complex surveys that are missing at rand