Learning Kolmogorov Models for Binary Random Variables
Machine Learning
2018-06-07 v1 Artificial Intelligence
Machine Learning
Abstract
We summarize our recent findings, where we proposed a framework for learning a Kolmogorov model, for a collection of binary random variables. More specifically, we derive conditions that link outcomes of specific random variables, and extract valuable relations from the data. We also propose an algorithm for computing the model and show its first-order optimality, despite the combinatorial nature of the learning problem. We apply the proposed algorithm to recommendation systems, although it is applicable to other scenarios. We believe that the work is a significant step toward interpretable machine learning.
Cite
@article{arxiv.1806.02322,
title = {Learning Kolmogorov Models for Binary Random Variables},
author = {Hadi Ghauch and Mikael Skoglund and Hossein Shokri-Ghadikolaei and Carlo Fischione and Ali H. Sayed},
journal= {arXiv preprint arXiv:1806.02322},
year = {2018}
}
Comments
9 pages, accecpted to ICML 2018: Workshop on Nonconvex Optimization