Fokker-Planck Equation
A partial differential equation describing the evolution of probability density in stochastic dynamical systems; in filtering theory it describes state transitions.
Timeline (last 90 days)
Using the same scaling matrix for both the drift term and the noise covariance ensures that the stationary solution of the Fokker-Planck equation is not altered by the scaling, thereby maintaining convergence to the correct target distribution.
The key tools for propagating score estimation error into a KL divergence bound on the path distribution are Girsanov's theorem and the Fokker-Planck equation, with compensated Poisson random measures additionally required for processes with jumps
All Facts (2)
Using the same scaling matrix for both the drift term and the noise covariance ensures that the stationary solution of the Fokker-Planck equation is not altered by the scaling, thereby maintaining convergence to the correct target distribution.
50%UnverifiedThe key tools for propagating score estimation error into a KL divergence bound on the path distribution are Girsanov's theorem and the Fokker-Planck equation, with compensated Poisson random measures additionally required for processes with jumps
50%