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... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIT.2018.2808161 | IEEE Transactions on Information Theory |
Keywords | Field | DocType |
Entropy,Density measurement,Atmospheric measurements,Particle measurements,Covariance matrices,Transportation,Information theory | Information theory,Entropy power inequality,Discrete mathematics,Mathematical analysis,Computer science,Quadratic equation,Gaussian,Mathematical proof,Atmospheric measurements,Spectral gap,Kullback–Leibler divergence | Journal |
Volume | Issue | ISSN |
64 | 8 | 0018-9448 |
Citations | PageRank | References |
2 | 0.40 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thomas A. Courtade | 1 | 2 | 0.74 |
Max Fathi | 2 | 2 | 0.40 |
Ashwin Pananjady | 3 | 40 | 9.69 |