This repository contains a code implementing functions that give lower bounds for the total variation(TV) distance [1] and the Hellinger distance [2] between two distributions given means and variances.
folder name | explanation |
---|---|
results | Comparison of the TV (or squared Hellinger) distance with lower bound. |
src | A code implementing functions that give lower bounds. |
docs | Summary of tight lower bounds for divergence measures between distributions with given means and variances. |
This project is licensed under the terms of the MIT license.
- [1] Nishiyama, Tomohiro. "Lower Bounds for the Total Variation Distance Between Arbitrary Distributions with Given Means and Variances." arXiv preprint arXiv:2212.05820 (2022).
- [2] Nishiyama, Tomohiro. "Tight Lower Bounds for
$\alpha $ -Divergences Under Moment Constraints and Relations Between Different$\alpha$ ." arXiv preprint arXiv:2105.12972 (2021).