Generalization Error Bounds on Deep Learning with Markov Datasets. (arXiv:2201.11059v1 [stat.ML])

In this paper, we derive upper bounds on generalization errors for deep
neural networks with Markov datasets. These bounds are developed based on
Koltchinskii and Panchenko's approach for bounding the generalization error of
combined classifiers with i.i.d. datasets. The development of new
symmetrization inequalities in high-dimensional probability for Markov chains
is a key element in our extension, where the pseudo-spectral gap of the
infinitesimal generator of the Markov chain plays as a key parameter in these
inequalities. We also propose …

arxiv datasets deep learning learning markov ml