Berry–Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms
Author:
Affiliation:
1. Department of Statistics and Data Scinece, Southern University of Science and Technology, Shenzhen, Guangdong, P.R. China
2. Department of Statistics, The Chinese University of Hong Kong, Shatin, N.T. Hong Kong
Publisher
Bernoulli Society for Mathematical Statistics and Probability
Subject
Statistics and Probability
Reference32 articles.
1. Vershynin, R. (2012). Introduction to the non-asymptotic analysis of random matrices. In Compressed Sensing 210–268. Cambridge: Cambridge Univ. Press.
2. Anastasiou, A., Balasubramanian, K. and Erdogdu, M.A. (2019). Normal approximation for stochastic gradient descent via non-asymptotic rates of martingale CLT. In Proceedings of the Thirty-Second Conference on Learning Theory. PMLR 99 115–137.
3. Bach, F. and Moulines, E. (2011). Non-asymptotic analysis of stochastic approximation algorithms for machine learning. In Neural Information Processing Systems (NIPS). Spain.
4. Barbour, A.D. (1990). Stein’s method for diffusion approximations. Probab. Theory Related Fields 84 297–322. 10.1007/BF01197887
5. Bentkus, V. (2003). On the dependence of the Berry-Esseen bound on dimension. J. Statist. Plann. Inference 113 385–402. 10.1016/S0378-3758(02)00094-0
Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Adaptive Powerball Stochastic Conjugate Gradient for Large-Scale Learning;IEEE Transactions on Big Data;2023-12
2. Bounds in L1 Wasserstein distance on the normal approximation of general M-estimators;Electronic Journal of Statistics;2023-01-01
3. Asymptotic normality and confidence region for Catoni's Z estimator;Stat;2022-12
4. Berry–Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms;Bernoulli;2022-08-01
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3