regarding the papers
L. Kontorovich, C.Cortes and M. Mohri. Kernel Methods for Learning Languages
. Theoretical Computer Science
405 (2008), pp. 223-236
L. Kontorovich, C.Cortes and M. Mohri. Learning Linearly Separable Languages
. In ALT
- Aug 2010: To achieve a proper bias-variance tradeoff (i.e., to avoid overfitting)
instead of defining the single kernel in equation (10)
we should have really considered a family of kernels , where the summation is over all shuffle ideals of length up to .
This technique is fleshed out here.