Properties of the strong data processing constant for Rényi divergence
Jin L, Esposito AR, Gastpar M. 2024. Properties of the strong data processing constant for Rényi divergence. Proceedings of the 2024 IEEE International Symposium on Information Theory. ISIT: International Symposium on Information Theory, 3178–3183.
Download (ext.)
Conference Paper
| Published
| English
Scopus indexed
Author
Jin, Lifu;
Esposito, Amedeo RobertoISTA;
Gastpar, Michael
Department
Abstract
Strong data processing inequalities (SDPI) are an important object of study in Information Theory and have been well studied for f -divergences. Universal upper and lower bounds have been provided along with several applications, connecting them to impossibility (converse) results, concentration of measure, hypercontractivity, and so on. In this paper, we study Renyi divergence and the corresponding SDPI constant whose behavior seems to deviate from that of ordinary <1>-divergences. In particular, one can find examples showing that the universal upper bound relating its SDPI constant to the one of Total Variation does not hold in general. In this work, we prove, however, that the universal lower bound involving the SDPI constant of the Chi-square divergence does indeed hold. Furthermore, we also provide a characterization of the distribution that achieves the supremum when is equal to 2 and consequently compute the SDPI constant for Renyi divergence of the general binary channel.
Publishing Year
Date Published
2024-08-19
Proceedings Title
Proceedings of the 2024 IEEE International Symposium on Information Theory
Acknowledgement
The work in this paper was supported in part by the Swiss National Science Foundation under Grant 200364.
Page
3178-3183
Conference
ISIT: International Symposium on Information Theory
Conference Location
Athens, Greece
Conference Date
2024-07-07 – 2024-07-12
ISBN
ISSN
IST-REx-ID
Cite this
Jin L, Esposito AR, Gastpar M. Properties of the strong data processing constant for Rényi divergence. In: Proceedings of the 2024 IEEE International Symposium on Information Theory. Institute of Electrical and Electronics Engineers; 2024:3178-3183. doi:10.1109/ISIT57864.2024.10619367
Jin, L., Esposito, A. R., & Gastpar, M. (2024). Properties of the strong data processing constant for Rényi divergence. In Proceedings of the 2024 IEEE International Symposium on Information Theory (pp. 3178–3183). Athens, Greece: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISIT57864.2024.10619367
Jin, Lifu, Amedeo Roberto Esposito, and Michael Gastpar. “Properties of the Strong Data Processing Constant for Rényi Divergence.” In Proceedings of the 2024 IEEE International Symposium on Information Theory, 3178–83. Institute of Electrical and Electronics Engineers, 2024. https://doi.org/10.1109/ISIT57864.2024.10619367.
L. Jin, A. R. Esposito, and M. Gastpar, “Properties of the strong data processing constant for Rényi divergence,” in Proceedings of the 2024 IEEE International Symposium on Information Theory, Athens, Greece, 2024, pp. 3178–3183.
Jin L, Esposito AR, Gastpar M. 2024. Properties of the strong data processing constant for Rényi divergence. Proceedings of the 2024 IEEE International Symposium on Information Theory. ISIT: International Symposium on Information Theory, 3178–3183.
Jin, Lifu, et al. “Properties of the Strong Data Processing Constant for Rényi Divergence.” Proceedings of the 2024 IEEE International Symposium on Information Theory, Institute of Electrical and Electronics Engineers, 2024, pp. 3178–83, doi:10.1109/ISIT57864.2024.10619367.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) to Main File(s)
Access Level
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Export
Marked PublicationsOpen Data ISTA Research Explorer
Sources
arXiv 2403.10656