A Fast and Robust Method for Global Topological Functional Optimization

Topological statistics, in the form of persistence diagrams, are a class of shape descriptors that capture global structural information in data. The mapping from data structures to persistence diagrams is almost everywhere differentiable, allowing for topological gradients to be backpropagated to ordinary gradients. However, as a method for optimizing a topological functional, this backpropagation method is expensive, unstable, and produces very fragile optima. Our contribution is to introduce a novel backpropagation scheme that is significantly faster, more stable, and produces more robust optima. Moreover, this scheme can also be used to produce a stable visualization of dots in a persistence diagram as a distribution over critical, and near-critical, simplices in the data structure.

[1]  Herbert Edelsbrunner,et al.  Computational Topology - an Introduction , 2009 .

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

[3]  Dimitris Samaras,et al.  Topology-Preserving Deep Image Segmentation , 2019, NeurIPS.

[4]  C. L. Zitnick,et al.  What does it mean to learn in deep networks ? And , how does one detect adversarial attacks ? , 2019 .

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Paul Bendich,et al.  Stabilizing the unstable output of persistent homology computations , 2015, Journal of Applied and Computational Topology.

[7]  Paul Schrater,et al.  Adversarial Examples Target Topological Holes in Deep Networks , 2019, ArXiv.

[8]  Valerio Pascucci,et al.  Persistence-sensitive simplification functions on 2-manifolds , 2006, SCG '06.

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

[10]  Kenneth A. Brown,et al.  Nonlinear Statistics of Human Speech Data , 2009, Int. J. Bifurc. Chaos.

[11]  Gunnar E. Carlsson,et al.  Topology and data , 2009 .

[12]  Adrian S. Lewis,et al.  A Robust Gradient Sampling Algorithm for Nonsmooth, Nonconvex Optimization , 2005, SIAM J. Optim..

[13]  Jennifer Gamble,et al.  Exploring uses of persistent homology for statistical analysis of landmark-based shape data , 2010, J. Multivar. Anal..

[14]  Karsten M. Borgwardt,et al.  Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology , 2018, ICLR.

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

[16]  Leonidas J. Guibas,et al.  Proximity of persistence modules and their diagrams , 2009, SCG '09.

[17]  Mathieu Carrière,et al.  PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures , 2020, AISTATS.

[18]  Ruslan Salakhutdinov,et al.  On Characterizing the Capacity of Neural Networks using Algebraic Topology , 2018, ArXiv.

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

[20]  J. Marron,et al.  Persistent Homology Analysis of Brain Artery Trees. , 2014, The annals of applied statistics.