arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.07467stat.MLcs.LGstat.COstat.ME
收藏

深度高斯马尔可夫随机场

Deep Gaussian Markov Random Fields

Linköping University(林雪平大学)

Per Sidén, Fredrik Lindsten

摘要:

高斯马尔可夫随机场(GMRF)是广泛用于空间统计学及相关领域的概率图模型,用于对空间结构的依赖性进行建模。我们建立了GMRF和卷积神经网络(CNN)之间的正式连接。常见的GMRF是生成模型的特殊情况,其中从数据到潜在变量的逆映射由1层线性CNN给出。这种连接允许我们将GMRF推广到多层CNN架构,以具有有利的计算缩放的方式有效地增加相应GMRF的阶数。我们描述了如何完善的工具,如autodiff和变分推断,可以用于简单有效的推理和学习的深度GMRF。我们证明了所提出的模型的灵活性,并表明它优于国家的最先进的卫星温度数据集,在预测和预测的不确定性。

英文摘要:

Gaussian Markov random fields (GMRFs) are probabilistic graphical models widely used in spatial statistics and related fields to model dependencies over spatial structures. We establish a formal connection between GMRFs and convolutional neural networks (CNNs). Common GMRFs are special cases of a generative model where the inverse mapping from data to latent variables is given by a 1-layer linear CNN. This connection allows us to generalize GMRFs to multi-layer CNN architectures, effectively increasing the order of the corresponding GMRF in a way which has favorable computational scaling. We describe how well-established tools, such as autodiff and variational inference, can be used for simple and efficient inference and learning of the deep GMRF. We demonstrate the flexibility of the proposed model and show that it outperforms the state-of-the-art on a dataset of satellite temperatures, in terms of prediction and predictive uncertainty.

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。

↑