Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise
Steinwart, Ingo ; Anghel, Marian
Ann. Statist., Tome 37 (2009) no. 1, p. 841-875 / Harvested from Project Euclid
We consider the problem of forecasting the next (observable) state of an unknown ergodic dynamical system from a noisy observation of the present state. Our main result shows, for example, that support vector machines (SVMs) using Gaussian RBF kernels can learn the best forecaster from a sequence of noisy observations if (a) the unknown observational noise process is bounded and has a summable α-mixing rate and (b) the unknown ergodic dynamical system is defined by a Lipschitz continuous function on some compact subset of ℝd and has a summable decay of correlations for Lipschitz continuous functions. In order to prove this result we first establish a general consistency result for SVMs and all stochastic processes that satisfy a mixing notion that is substantially weaker than α-mixing.
Publié le : 2009-04-15
Classification:  Observational noise model,  forecasting dynamical systems,  support vector machines,  consistency,  62M20,  37D25,  37C99,  37M10,  60K99,  62M10,  62M45,  68Q32,  68T05
@article{1236693152,
     author = {Steinwart, Ingo and Anghel, Marian},
     title = {Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise},
     journal = {Ann. Statist.},
     volume = {37},
     number = {1},
     year = {2009},
     pages = { 841-875},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1236693152}
}
Steinwart, Ingo; Anghel, Marian. Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise. Ann. Statist., Tome 37 (2009) no. 1, pp.  841-875. http://gdmltest.u-ga.fr/item/1236693152/