English

Self-Averaging and On-line Learning

Disordered Systems and Neural Networks 2009-10-31 v1 Statistical Mechanics

Abstract

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.

Keywords

Cite

@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}
}

Comments

10 pages