3 papers
cs.LG2026
Optimal Stability of KL Divergence under Gaussian Perturbations
Jialu Pan, Yufeng Zhang, Nan Hu +3
We study the problem of characterizing the stability of Kullback-Leibler (KL) divergence under Gaussian perturbations beyond Gaussian families. Existing relaxed triangle inequaliti…
cs.IT2021
On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
Yufeng Zhang, Wanwei Liu, Zhenbang Chen +2
Kullback-Leibler (KL) divergence is one of the most important divergence measures between probability distributions. In this paper, we prove several properties of KL divergence bet…
cs.LG2020
Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models
Yufeng Zhang, Jialu Pan, Wanwei Liu +5
Recent research has revealed that deep generative models including flow-based models and Variational Autoencoders may assign higher likelihoods to out-of-distribution (OOD) data th…