Herding Dynamic Weights for Partially Observed Random Field Models

05/09/2012
by   Max Welling, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset