A PROBABILITY APPROXIMATION FRAMEWORK: MARKOV PROCESS APPROACH

被引：1

作者：

Chen, Peng ^{[1
]}

Shao, Qi-Man ^{[2
]}

Xu, Lihu ^{[3
]}

机构：

[1] Nanjing Univ Aeronaut & Astronaut, Coll Math, Nanjing, Peoples R China

[2] Southern Univ Sci & Technol, Dept Stat & Data Sci, SICM, NCAMS, Shenzhen, Peoples R China

[3] Univ Macau, Fac Sci & Technol, Dept Math, Zhuhai, Peoples R China

来源：

ANNALS OF APPLIED PROBABILITY | 2023年 / 33卷 / 02期

关键词：

Probability approximation; Markov process; It??s formula; online stochastic gradient descent; stochastic differential equation; Euler-Maruyama (EM) discretization; stable process; normal approxi-mation; Wasserstein-1; distance; MULTIVARIATE NORMAL APPROXIMATION; STEINS METHOD; POISSON APPROXIMATION; INVARIANT-MEASURES; MATRICES; ERGODICITY; EQUATIONS; DISTANCE; MODEL;

D O I：

10.1214/22-AAP1853

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We view the classical Lindeberg principle in a Markov process setting to establish a probability approximation framework by the associated Ito's for-mula and Markov operator. As applications, we study the error bounds of the following three approximations: approximating a family of online stochastic gradient descents (SGDs) by a stochastic differential equation (SDE) driven by multiplicative Brownian motion, Euler-Maruyama (EM) discretization for multi-dimensional Ornstein-Uhlenbeck stable process and multivariate nor-mal approximation. All these error bounds are in Wasserstein-1 distance.

引用

页码：1419 / 1459

页数：41

共 50 条

[1] QUANTITATIVE APPROXIMATION OF THE PROBABILITY DISTRIBUTION OF A MARKOV PROCESS BY FORMAL ABSTRACTIONS
Soudjani, Sadegh Esmeil Zadeh
Abate, Alessandro
LOGICAL METHODS IN COMPUTER SCIENCE, 2015, 11 (03)
[2] A new approach in analyzing extinction probability of Markov branching process with immigration and migration
Anyue Chen
Xiliu Li
HoMing Ku
Frontiers of Mathematics in China, 2015, 10 : 733 - 751
[3] On the approximation of Markov chains to determine the probability of extinction of a genotype
Orman, GV
ICCIMA 2005: Sixth International Conference on Computational Intelligence and Multimedia Applications, Proceedings, 2005, : 68 - 73
[4] A new approach in analyzing extinction probability of Markov branching process with immigration and migration
Chen, Anyue
Li, Xiliu
Ku, HoMing
FRONTIERS OF MATHEMATICS IN CHINA, 2015, 10 (04) : 733 - 751
[5] A Multinomial Approximation Approach for the Finite Time Survival Probability Under the Markov-modulated Risk Model
Li, Jingchao
Su, Bihao
Wei, Zhenghong
Nie, Ciyu
METHODOLOGY AND COMPUTING IN APPLIED PROBABILITY, 2022, 24 (03) : 2169 - 2194
[6] A Multinomial Approximation Approach for the Finite Time Survival Probability Under the Markov-modulated Risk Model
Jingchao Li
Bihao Su
Zhenghong Wei
Ciyu Nie
Methodology and Computing in Applied Probability, 2022, 24 : 2169 - 2194
[7] Minimizing the Outage Probability in a Markov Decision Process
Corlay, Vincent
Sibel, Jean-Christophe
2023 IEEE INFORMATION THEORY WORKSHOP, ITW, 2023, : 107 - 112
[8] The probability distribution associated with the dichotornic Markov process
Williams, M. M. R.
JOURNAL OF QUANTITATIVE SPECTROSCOPY & RADIATIVE TRANSFER, 2008, 109 (10): : 1771 - 1777
[9] AN APPROXIMATION TO THE STATIONARY DISTRIBUTION OF A MULTIDIMENSIONAL MARKOV PROCESS
ALBRIGHT, SC
SONI, A
IIE TRANSACTIONS, 1988, 20 (01) : 111 - 118
[10] A Markov Chain Framework for Cycle Time Approximation of Toolsets
Akhavan-Tabatabaei, Raha
Fathi, Yahya
Shanthikumar, J. George
IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2012, 25 (04) : 589 - 597

← 1 2 3 4 5 →