Generalization and robustness of batched weighted average algorithm with V-geometrically ergodic Markov data Conference

Cuong, NV, Ho, LST, Dinh, V. (2013). Generalization and robustness of batched weighted average algorithm with V-geometrically ergodic Markov data . Lecture Notes in Computer Science, 8139 LNAI 264-278. 10.1007/978-3-642-40935-6_19

cited authors

  • Cuong, NV; Ho, LST; Dinh, V

abstract

  • We analyze the generalization and robustness of the batched weighted average algorithm for V-geometrically ergodic Markov data. This algorithm is a good alternative to the empirical risk minimization algorithm when the latter suffers from overfitting or when optimizing the empirical risk is hard. For the generalization of the algorithm, we prove a PAC-style bound on the training sample size for the expected L1-loss to converge to the optimal loss when training data are V-geometrically ergodic Markov chains. For the robustness, we show that if the training target variable's values contain bounded noise, then the generalization bound of the algorithm deviates at most by the range of the noise. Our results can be applied to the regression problem, the classification problem, and the case where there exists an unknown deterministic target hypothesis. © 2013 Springer-Verlag.

authors

publication date

  • November 18, 2013

published in

Digital Object Identifier (DOI)

start page

  • 264

end page

  • 278

volume

  • 8139 LNAI