English

New Upper bounds for KL-divergence Based on Integral Norms

Probability 2024-10-31 v2 Information Theory math.IT

Abstract

In this paper, some new upper bounds for Kullback-Leibler divergence(KL-divergence) based on L1,L2L^1, L^2 and LL^\infty norms of density functions are discussed. Our findings unveil that the convergence in KL-divergence sense sandwiches between the convergence of density functions in terms of L1L^1 and L2L^2 norms. Furthermore, we endeavor to apply our newly derived upper bounds to the analysis of the rate theorem of the entropic conditional central limit theorem.

Keywords

Cite

@article{arxiv.2409.00934,
  title  = {New Upper bounds for KL-divergence Based on Integral Norms},
  author = {Liuquan Yao and Songhao Liu},
  journal= {arXiv preprint arXiv:2409.00934},
  year   = {2024}
}

Comments

25

R2 v1 2026-06-28T18:30:56.170Z