Self-Averaging and On-line Learning
无序系统与神经网络
2009-10-31 v1 统计力学
摘要
Conditions are given under which one may prove that the stochastic dynamics of on-line learning can be described by the deterministic evolution of a finite set of order parameters in the thermodynamic limit. A global constraint on the average magnitude of the increments in the stochastic process is necessary to ensure self-averaging. In the absence of such a constraint, convergence may only be in probability.
引用
@article{arxiv.cond-mat/9805339,
title = {Self-Averaging and On-line Learning},
author = {G. Reents and R. Urbanczik},
journal= {arXiv preprint arXiv:cond-mat/9805339},
year = {2009}
}
备注
10 pages