Concentration inequalities for regenerative and Harris recurrent Markov chains with applications to statistical learning.
vendredi 22 mars 2019, 9h30 - 10h30
Concentration inequalities are very often a crucial step in deriving many results in statistical learning. The purpose of this talk is to present exponential and polynomial tail maximal inequalities for regenerative Markov chains. All constants involved in the bounds are given in an explicit form which can be advantageous in practical considerations. We show that the inequalities obtained for regenerative Markov chains can be easily generalized to a Harris recurrent case. Furthermore, we provide one example of application of presented inequalities in statistical learning theory and obtain generalization bounds for mimimum volume set estimation problem when the data are Markovian. Minimum volume set estimation problem is (unsupervised) anomaly/novelty detection algorithm used in a setting when we deal with unlabelled dataset.