arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.05485cs.ITcs.AImath.IT
收藏

多元高斯分布Kullback-Leibler发散的性质

On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions

Hunan University(湖南大学);National University of Defense Technology(国防科技大学);State Key Laboratory of High Performance Computing, National University of Defense Technology(国防科技大学高性能计算国家重点实验室)

Yufeng Zhang, Wanwei Liu, Zhenbang Chen, Ji Wang, Kenli Li

摘要:

Kullback-Leibler(KL)散度是概率分布之间最重要的散度度量之一。本文证明了多元高斯分布之间KL散度的几个性质。首先,对任意两个$n$维高斯分布$\mathcal{N}_1$和$\mathcal{N}_2$,我们给出了当$KL(\mathcal{N}_1||\mathcal{N}_2)$.对于小的$\varepsilon$,我们证明了上确界是$\varepsilon + 2\varepsilon^{1.5} + O(\varepsilon^2)$。这量化了高斯之间的小KL发散的近似对称性。当$KL(\mathcal{N}_1||\mathcal{N}_2)$.给出了上确界和下确界可达的条件。第二,对于任意三个$n$维高斯分布的$\mathcal{N}_1$,$\mathcal{N}_2$,和$\mathcal{N}_3$,如果$KL(\mathcal{N}_1||\mathcal{N}_2)\leq \varepsilon_1$和$\varepsilon_1,\varepsilon_2\ge 0$的$KL(\mathcal{N}_2||\mathcal{N}_3)\leq \varepsilon_2$,我们找到了$KL(\mathcal{N}_1||\mathcal{N}_3)$的上界.对于小的$\varepsilon_1$和$\varepsilon_2$,我们证明了上界是$3\varepsilon_1+3\varepsilon_2+2\sqrt{\varepsilon_1\varepsilon_2}+o(\varepsilon_1)+o(\varepsilon_2)$。这表明高斯之间的KL分歧遵循一个放松的三角不等式。重要的是,本文中给出的定理中的所有界都与维数$n$无关。最后,我们讨论了我们的定理在解释基于流模型的反直觉现象,推导深度异常检测算法,以及将一步鲁棒性保证扩展到安全强化学习的多步中的应用。

英文摘要:

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 between multivariate Gaussian distributions. First, for any two $n$-dimensional Gaussian distributions $\mathcal{N}_1$ and $\mathcal{N}_2$, we give the supremum of $KL(\mathcal{N}_1||\mathcal{N}_2)$ when $KL(\mathcal{N}_2||\mathcal{N}_1)\leq \varepsilon\ (\varepsilon>0)$. For small $\varepsilon$, we show that the supremum is $\varepsilon + 2\varepsilon^{1.5} + O(\varepsilon^2)$. This quantifies the approximate symmetry of small KL divergence between Gaussians. We also find the infimum of $KL(\mathcal{N}_1||\mathcal{N}_2)$ when $KL(\mathcal{N}_2||\mathcal{N}_1)\geq M\ (M>0)$. We give the conditions when the supremum and infimum can be attained. Second, for any three $n$-dimensional Gaussians $\mathcal{N}_1$, $\mathcal{N}_2$, and $\mathcal{N}_3$, we find an upper bound of $KL(\mathcal{N}_1||\mathcal{N}_3)$ if $KL(\mathcal{N}_1||\mathcal{N}_2)\leq \varepsilon_1$ and $KL(\mathcal{N}_2||\mathcal{N}_3)\leq \varepsilon_2$ for $\varepsilon_1,\varepsilon_2\ge 0$. For small $\varepsilon_1$ and $\varepsilon_2$, we show the upper bound is $3\varepsilon_1+3\varepsilon_2+2\sqrt{\varepsilon_1\varepsilon_2}+o(\varepsilon_1)+o(\varepsilon_2)$. This reveals that KL divergence between Gaussians follows a relaxed triangle inequality. Importantly, all the bounds in the theorems presented in this paper are independent of the dimension $n$. Finally, We discuss the applications of our theorems in explaining counterintuitive phenomenon of flow-based model, deriving deep anomaly detection algorithm, and extending one-step robustness guarantee to multiple steps in safe reinforcement learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑