arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.13083cs.LGcs.AIstat.ML
收藏

变分推理导论

An Introduction to Variational Inference

Sertis Vision Lab(Sertis视觉实验室)

Ankush Ganguly, Samuel W. F. Earp

摘要:

复概率密度的近似是现代统计学中的一个核心问题。在本文中,我们介绍了变分推理(VI)的概念,这是机器学习中的一种流行方法,它使用优化技术来估计复概率密度。这一特性使VI比经典方法(如马尔可夫链蒙特卡罗采样)收敛得更快。从概念上讲,VI的工作原理是选择一系列概率密度函数,然后找到最接近实际概率密度的函数-通常使用Kullback-Leibler(KL)散度作为优化度量。我们引入证据下界来计算近似的概率密度,并回顾了平均场变分推理背后的思想。最后,我们讨论了虚拟仪器在变分自动编码器(VAE)和VAE-生成对抗网络(VAE-GAN)中的应用。通过本文,我们的目的是解释VI的概念,并协助未来的研究与这种方法。

英文摘要:

Approximating complex probability densities is a core problem in modern statistics. In this paper, we introduce the concept of Variational Inference (VI), a popular method in machine learning that uses optimization techniques to estimate complex probability densities. This property allows VI to converge faster than classical methods, such as, Markov Chain Monte Carlo sampling. Conceptually, VI works by choosing a family of probability density functions and then finding the one closest to the actual probability density -- often using the Kullback-Leibler (KL) divergence as the optimization metric. We introduce the Evidence Lower Bound to tractably compute the approximated probability density and we review the ideas behind mean-field variational inference. Finally, we discuss the applications of VI to variational auto-encoders (VAE) and VAE-Generative Adversarial Network (VAE-GAN). With this paper, we aim to explain the concept of VI and assist in future research with this approach.

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。

↑