Forecasting the Evolution of Dynamical Systems from Noisy Observations

Details Forecasting the Evolution of Dynamical Systems from Noisy Observations Forecasting the Evolution of Dynamical Systems from Noisy Observations

2007-07-27

arxiv.org/abs/0707.4146v1

Nonlinear Sciences

Chaotic Dynamics

5 pages, 4 figures, 1 table

Scientific paper

We consider the problem of designing almost optimal predictors for dynamical systems from a finite sequence of noisy observations and incomplete knowledge of the dynamics and the noise. We first discuss the properties of the optimal (Bayes) predictor and present the limitations of memory-free forecasting methods, and of any finite memory methods in general. We then show that a nonparametric support vector machine approach to forecasting can consistently learn the optimal predictor for all pairs of dynamical systems and bounded observational noise processes that possess summable correlation sequences. Numerical experiments show that this approach adapts the memory length of the forecaster to the complexity of the learning task and the size of the observation sequence.

Affiliated with

Also associated with

No associations

Rating

Forecasting the Evolution of Dynamical Systems from Noisy Observations does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Forecasting the Evolution of Dynamical Systems from Noisy Observations, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Forecasting the Evolution of Dynamical Systems from Noisy Observations will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-272166