Decoupling and Self-Normalization with an application to Machine Learning and Kolmogorov's Law of the Iterated Logarithm
Authors: Victor de la Pena
Abstract: In this talk I will present an introduction to the Theory of Decoupling and Self-normalization and show how Self-normalization has been used on Machine Learning. In addition, I will present a symmetrized extension of Kolmogorov's Law of the Iterated Logarithm without moment or dependence assumptions.