Journée Mathematical Foundations of Learning Theory
< précédent | suivant >
|Learning from Dependent Observations|
Ingo Steinwart (Los Alamos National Laboratory)
1er juin 2006
The standard assumption in statistical learning theory is that the available samples are realizations of i.i.d. random variables. However, in many applications this assumption cannot be rigorously justified, in particular if the observations are intrinsically temporal. In this talk I will present some recent results on the learnability of rather general observation-generating random processes. In particular, I will establish a weak consistency result for support vector machine classification and regression. In addition, refined results for e.g. α-mixing processes will be presented. If time permits I will finally discuss whether the behaviour of certain dynamical systems can be learned.
||Ingo Steinwart (Los Alamos National Laboratory)|
Machine Learning & Pattern Recognition Team in the Modeling, Algorithms, and Informatics Group