arXiv · cond-mat/9805339
Self-Averaging and On-line Learning
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
G. Reents, R. Urbanczik. 1998-05-26. Self-Averaging and On-line Learning. https://doi.org/10.1103/physrevlett.80.5445
Cite the original work for its findings. Save a collection to share your selection of sources.