English

$f$-Divergence Inequalities via Functional Domination

Information Theory 2016-10-31 v1 Machine Learning math.IT Probability Statistics Theory Statistics Theory

Abstract

This paper considers derivation of ff-divergence inequalities via the approach of functional domination. Bounds on an ff-divergence based on one or several other ff-divergences are introduced, dealing with pairs of probability measures defined on arbitrary alphabets. In addition, a variety of bounds are shown to hold under boundedness assumptions on the relative information. The journal paper, which includes more approaches for the derivation of f-divergence inequalities and proofs, is available on the arXiv at https://arxiv.org/abs/1508.00335, and it has been published in the IEEE Trans. on Information Theory, vol. 62, no. 11, pp. 5973-6006, November 2016.

Keywords

Cite

@article{arxiv.1610.09110,
  title  = {$f$-Divergence Inequalities via Functional Domination},
  author = {Igal Sason and Sergio Verdú},
  journal= {arXiv preprint arXiv:1610.09110},
  year   = {2016}
}

Comments

A conference paper, 5 pages. To be presented in the 2016 ICSEE International Conference on the Science of Electrical Engineering, Nov. 16--18, Eilat, Israel. See https://arxiv.org/abs/1508.00335 for the full paper version, published as a journal paper in the IEEE Trans. on Information Theory, vol. 62, no. 11, pp. 5973-6006, November 2016

R2 v1 2026-06-22T16:34:58.827Z