Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams

Abstract

Algebraic topology methods have recently played an important role for statistical analysis with complicated geometric structured data such as shapes, linked twist maps, and material data. Among them, \textit{persistent homology} is a well-known tool to extract robust topological features, and outputs as \textit{persistence diagrams} (PDs). However, PDs are point multi-sets which can not be used in machine learning algorithms for vector data. To deal with it, an emerged approach is to use kernel methods, and an appropriate geometry for PDs is an important factor to measure the similarity of PDs. A popular geometry for PDs is the \textit{Wasserstein metric}. However, Wasserstein distance is not \textit{negative definite}. Thus, it is limited to build positive definite kernels upon the Wasserstein distance \textit{without approximation}. In this work, we rely upon the alternative \textit{Fisher information geometry} to propose a positive definite kernel for PDs \textit{without approximation}, namely the Persistence Fisher (PF) kernel. Then, we analyze eigensystem of the integral operator induced by the proposed kernel for kernel machines. Based on that, we derive generalization error bounds via covering numbers and Rademacher averages for kernel machines with the PF kernel. Additionally, we show some nice properties such as stability and infinite divisibility for the proposed kernel. Furthermore, we also propose a linear time complexity over the number of points in PDs for an approximation of our proposed kernel with a bounded error. Throughout experiments with many different tasks on various benchmark datasets, we illustrate that the PF kernel compares favorably with other baseline kernels for PDs.

arXiv commentto appear at the 32nd Conference on Neural Information Processing Systems (NIPS), Canada, 2018. (Camera-ready version)

Cited by in corpus (18)

• Scalar Field Comparison with Topological Descriptors: Properties and Applications for Scientific Visualization
• PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures
• The persistence landscape and some of its properties
• Learning metrics for persistence-based summaries and applications for graph classification
• giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration
• Topological Persistence Machine of Phase Transitions
• Leveraging the Mathematics of Shape for Solar Magnetic Eruption Prediction
• Adaptive Partitioning for Template Functions on Persistence Diagrams
• RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds
• Fuzzy c-Means Clustering for Persistence Diagrams
• Euler Characteristic Tools For Topological Data Analysis
• Understanding the Power of Persistence Pairing via Permutation Test
• Persistence B-Spline Grids: Stable Vector Representation of Persistence Diagrams Based on Data Fitting
• ATOL: Measure Vectorization for Automatic Topologically-Oriented Learning
• Tree-Sliced Variants of Wasserstein Distances
• Learning Hyperbolic Representations of Topological Features
• Entropy Partial Transport with Tree Metrics: Theory and Practice
• Topological Bayesian Optimization with Persistence Diagrams