Rate of Convergence of Truncated Stochastic Approximation Procedures with Moving Bounds
Statistics Theory
2016-11-14 v2 Statistics Theory
Abstract
The paper is concerned with stochastic approximation procedures having three main characteristics: truncations with random moving bounds, a matrix valued random step-size sequence, and a dynamically changing random regression function. We study convergence and rate of convergence. Main results are supplemented with corollaries to establish various sets of sufficient conditions, with the main emphases on the parametric statistical estimation. The theory is illustrated by examples and special cases.
Keywords
Cite
@article{arxiv.1508.01902,
title = {Rate of Convergence of Truncated Stochastic Approximation Procedures with Moving Bounds},
author = {Teo Sharia and Lei Zhong},
journal= {arXiv preprint arXiv:1508.01902},
year = {2016}
}
Comments
30 pages