Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
Herding Dynamic Weights for Partially Observed Random Field Models
Max Welling
Abstract:
Learning the parameters of a (potentially partially observable) random field model is intractable in general. Instead of focussing on a single optimal parameter value we propose to treat parameters as dynamical quantities. We introduce an algorithm to generate complex dynamics for parameters and (both visible and hidden) state vectors. We show that under certain conditions averages computed over trajectories of the proposed dynamical system converge to averages computed over the data. Our "herding dynamics" does not require expensive operations such as exponentiation and is fully deterministic.
Keywords: null
Pages: 599-606
PS Link:
PDF Link: /papers/09/p599-welling.pdf
BibTex:
@INPROCEEDINGS{Welling09,
AUTHOR = "Max Welling ",
TITLE = "Herding Dynamic Weights for Partially Observed Random Field Models",
BOOKTITLE = "Proceedings of the Twenty-Fifth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-09)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2009",
PAGES = "599--606"
}


hosted by DSL   •   site info   •   help