Quantitative Stability of the Entropy Power Inequality

Thomas A. Courtade, Max Fathi, Ashwin PananjadyIEEE Trans. Information Theory 2018 · DOI · OpenReview

Abstract

We establish quantitative stability results for the entropy power inequality (EPI). Specifically, we show that if uniformly log-concave densities nearly saturate the EPI, then they must be close to Gaussian densities in the quadratic Kantorovich-Wasserstein distance. Furthermore, if one of the densities is Gaussian and the other is log-concave, or more generally has positive spectral gap, then the deficit in the EPI can be controlled in terms of the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -Kantorovich-Wasserstein distance or relative entropy, respectively. As a counterpoint, an example shows that the EPI can be unstable with respect to the quadratic Kantorovich-Wasserstein distance when densities are uniformly log-concave on sets of measure arbitrarily close to one. Our stability results can be extended to non-log-concave densities, provided certain regularity conditions are met. The proofs are based on mass transportation.
BibTeX
@article{courtade2018quantitative,
  author = {Thomas A. Courtade and Max Fathi and Ashwin Pananjady},
  title = {{Quantitative Stability of the Entropy Power Inequality}},
  journal = {IEEE Trans. Information Theory},
  year = {2018},
  doi = {10.1109/tit.2018.2808161},
}

Loading related content...

Figure