Loading...
Please wait, while we are loading the content...
Similar Documents
Skewed Jensen—Fisher Divergence and Its Bounds
| Content Provider | MDPI |
|---|---|
| Author | Yamano, Takuya |
| Copyright Year | 2021 |
| Description | A non-uniform (skewed) mixture of probability density functions occurs in various disciplines. One needs a measure of similarity to the respective constituents and its bounds. We introduce a skewed Jensen–Fisher divergence based on relative Fisher information, and provide some bounds in terms of the skewed Jensen–Shannon divergence and of the variational distance. The defined measure coincides with the definition from the skewed Jensen–Shannon divergence via the de Bruijn identity. Our results follow from applying the logarithmic Sobolev inequality and Poincaré inequality. |
| Ending Page | 264 |
| Page Count | 9 |
| Starting Page | 256 |
| e-ISSN | 26739321 |
| DOI | 10.3390/foundations1020018 |
| Journal | Foundations |
| Issue Number | 2 |
| Volume Number | 1 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-11-16 |
| Access Restriction | Open |
| Subject Keyword | Foundations Mathematical Social Sciences Skewed Jensen–fisher Divergence Relative Fisher Information Fisher Information Logarithmic Sobolev Inequality Poincaré Inequality |
| Content Type | Text |
| Resource Type | Article |
