arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09035cs.LGcond-mat.dis-nncs.CV
收藏

用于鲁棒主图学习的混合模型正则化

Regularization of Mixture Models for Robust Principal Graph Learning

Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);Universidad Complutense(马德里康普顿斯大学)

Tony Bonnaire, Aurélien Decelle, Nabila Aghanim

AI总结:

提出正则化混合模型,将图拓扑作为高斯簇先验,利用 EM 在多项式时间内学习鲁棒主图,并通过随机子采样扩展最小生成树以处理环。

摘要:

本文提出了一种正则化版本的 Mixture Models(混合模型),用于从 D 维数据点的分布中学习主图。在面向脊线检测的流形学习这一特定情形中,我们假设底层流形可以建模为一种图结构,该结构充当 Gaussian clusters(高斯簇)的拓扑先验,从而将该问题转化为最大后验估计。模型参数通过 Expectation-Maximization(期望最大化)过程进行迭代估计,使结构学习在计算上高效,并且对于任意图先验都能保证在多项式时间内收敛。我们还在该形式体系中嵌入了一种自然方式,使算法对模式中的异常值以及与图结构一致的流形采样异方差性具有鲁棒性。该方法使用由 minimum spanning tree(最小生成树)给出的图先验,并通过对数据集进行随机二次采样对其加以扩展,以考虑空间分布中可能观察到的环。

英文摘要:

A regularized version of Mixture Models is proposed to learn a principal graph from a distribution of $D$-dimensional data points. In the particular case of manifold learning for ridge detection, we assume that the underlying manifold can be modeled as a graph structure acting like a topological prior for the Gaussian clusters turning the problem into a maximum a posteriori estimation. Parameters of the model are iteratively estimated through an Expectation-Maximization procedure making the learning of the structure computationally efficient with guaranteed convergence for any graph prior in a polynomial time. We also embed in the formalism a natural way to make the algorithm robust to outliers of the pattern and heteroscedasticity of the manifold sampling coherently with the graph structure. The method uses a graph prior given by the minimum spanning tree that we extend using random sub-samplings of the dataset to take into account cycles that can be observed in the spatial distribution.

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。

↑