Wasserstein Stability for Persistence Diagrams

The stability of persistence diagrams is among the most important results in applied and computational topology. Most results in the literature phrase stability in terms of the bottleneck distance between diagrams and the $\infty$-norm of perturbations. This has two main implications: it makes the space of persistence diagrams rather pathological and it is often provides very pessimistic bounds with respect to outliers. In this paper, we provide new stability results with respect to the $p$-Wasserstein distance between persistence diagrams. This includes an elementary proof for the setting of functions on sufficiently finite spaces in terms of the $p$-norm of the perturbations, along with an algebraic framework for $p$-Wasserstein distance which extends the results to wider class of modules. We also provide apply the results to a wide range of applications in topological data analysis (TDA) including topological summaries, persistence transforms and the special but important case of Vietoris-Rips complexes.

[1]  D. J. H. Garling,et al.  The Cauchy-Schwarz Master Class: An Introduction to the Art of Mathematical Inequalities by J. Michael Steele , 2005, Am. Math. Mon..

[2]  Henry Adams,et al.  Persistence Images: A Stable Vector Representation of Persistent Homology , 2015, J. Mach. Learn. Res..

[3]  Chao Chen,et al.  A Topological Regularizer for Classifiers via Persistent Homology , 2019, AISTATS.

[4]  Chao Chen,et al.  Diffusion runs low on persistence fast , 2011, 2011 International Conference on Computer Vision.

[5]  Gunnar E. Carlsson,et al.  Zigzag Persistence , 2008, Found. Comput. Math..

[6]  Ulrich Bauer,et al.  Induced Matchings of Barcodes and the Algebraic Stability of Persistence , 2013, SoCG.

[7]  Vin de Silva,et al.  Metrics for Generalized Persistence Modules , 2013, Found. Comput. Math..

[8]  Erin W. Chambers,et al.  Vietoris–Rips Complexes of Planar Point Sets , 2009, Discret. Comput. Geom..

[9]  Alexander Russell,et al.  Computational topology: ambient isotopic approximation of 2-manifolds , 2003, Theor. Comput. Sci..

[10]  Steve Oudot,et al.  A Framework for Differential Calculus on Persistence Barcodes , 2019, Foundations of Computational Mathematics.

[11]  Primoz Skraba,et al.  Randomly Weighted d-Complexes: Minimal Spanning Acycles and Persistence Diagrams , 2017, Electron. J. Comb..

[12]  Ulrich Bauer,et al.  A stable multi-scale kernel for topological machine learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Vin de Silva,et al.  The observable structure of persistence modules , 2014, 1405.5644.

[14]  Katharine Turner,et al.  Principal component analysis of persistent homology rank functions with case studies of spatial point patterns, sphere packing and colloids , 2015, 1507.01454.

[15]  S. Mukherjee,et al.  Persistent Homology Transform for Modeling Shapes and Surfaces , 2013, 1310.1030.

[16]  Steve Oudot,et al.  On Rectangle-Decomposable 2-Parameter Persistence Modules , 2020, Discrete & Computational Geometry.

[17]  David Cohen-Steiner,et al.  Vines and vineyards by updating persistence in linear time , 2006, SCG '06.

[18]  W. Crawley-Boevey.  Decomposition of pointwise finite-dimensional persistence modules , 2012, 1210.0819.

[19]  Herbert Edelsbrunner,et al.  Topological Persistence and Simplification , 2000, Proceedings 41st Annual Symposium on Foundations of Computer Science.

[20]  Kenji Fukumizu,et al.  Persistence weighted Gaussian kernel for topological data analysis , 2016, ICML.

[21]  Peter Bubenik,et al.  Statistical topological data analysis using persistence landscapes , 2012, J. Mach. Learn. Res..

[22]  Steve Oudot,et al.  The Structure and Stability of Persistence Modules , 2012, Springer Briefs in Mathematics.

[23]  Peter Bubenik,et al.  Topological spaces of persistence modules and their properties , 2018, J. Appl. Comput. Topol..

[24]  Peter Bubenik,et al.  Categorification of Persistent Homology , 2012, Discret. Comput. Geom..

[25]  Steve Oudot,et al.  Persistence stability for geometric complexes , 2012, ArXiv.

[26]  Sara Kalisnik,et al.  Tropical Coordinates on the Space of Persistence Barcodes , 2019, Found. Comput. Math..

[27]  Maks Ovsjanikov,et al.  Topological Function Optimization for Continuous Shape Matching , 2018, Comput. Graph. Forum.

[28]  Amit Patel,et al.  Generalized persistence diagrams , 2016, J. Appl. Comput. Topol..

[29]  Marc Niethammer,et al.  Learning Representations of Persistence Barcodes , 2019, J. Mach. Learn. Res..

[30]  Yu-Min Chung,et al.  Persistence Curves: A canonical framework for summarizing persistence diagrams , 2019, Advances in Computational Mathematics.

[31]  Rachel Levanger,et al.  Persistent homology and Euler integral transforms , 2018, J. Appl. Comput. Topol..

[32]  Primoz Skraba,et al.  An Approximate Nerve Theorem , 2016, Foundations of Computational Mathematics.

[33]  Steve Oudot,et al.  Sliced Wasserstein Kernel for Persistence Diagrams , 2017, ICML.

[34]  Guandong Xu,et al.  Polynomial Representation for Persistence Diagram , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  David Cohen-Steiner,et al.  Lipschitz Functions Have Lp-Stable Persistence , 2010, Found. Comput. Math..

[36]  Sayan Mukherjee,et al.  How Many Directions Determine a Shape and other Sufficiency Results for Two Topological Transforms , 2018, Transactions of the American Mathematical Society, Series B.

[37]  Afra Zomorodian,et al.  Computational topology , 2010 .

[38]  Andreas Uhl,et al.  Deep Learning with Topological Signatures , 2017, NIPS.

[39]  David Cohen-Steiner,et al.  Stability of Persistence Diagrams , 2005, Discret. Comput. Geom..