Regularization of Persistent Homology Gradient Computation

Persistent homology is a method for computing the topological features present in a given data. Recently, there has been much interest in the integration of persistent homology as a computational step in neural networks or deep learning. In order for a given computation to be integrated in such a way, the computation in question must be differentiable. Computing the gradients of persistent homology is an ill-posed inverse problem with infinitely many solutions. Consequently, it is important to perform regularization so that the solution obtained agrees with known priors. In this work we propose a novel method for regularizing persistent homology gradient computation through the addition of a grouping term. This has the effect of helping to ensure gradients are defined with respect to larger entities and not individual points.

[1]  R. Ghrist.  Barcodes: The persistent topology of data , 2007 .

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

[3]  Vin de Silva,et al.  On the Local Behavior of Spaces of Natural Images , 2007, International Journal of Computer Vision.

[4]  G. Carlsson,et al.  Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survival , 2011, Proceedings of the National Academy of Sciences.

[6]  Carola-Bibiane Schönlieb,et al.  Adversarial Regularizers in Inverse Problems , 2018, NeurIPS.

[7]  Chao Chen,et al.  TopoGAN: A Topology-Aware Generative Adversarial Network , 2020, ECCV.

[8]  Milind Tambe,et al.  MIPaaL: Mixed Integer Program as a Layer , 2019, AAAI.

[9]  Steve Oudot,et al.  Inverse Problems in Topological Persistence , 2018, Topological Data Analysis.

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

[11]  Paul Bendich,et al.  A Fast and Robust Method for Global Topological Functional Optimization , 2020, ArXiv.

[12]  Mason A. Porter,et al.  A roadmap for the computation of persistent homology , 2015, EPJ Data Science.

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

[14]  Leonidas J. Guibas,et al.  A Topology Layer for Machine Learning , 2019, AISTATS.

[15]  Karsten M. Borgwardt,et al.  Topological Autoencoders , 2019, ICML.

[16]  Steve Oudot,et al.  A Framework for Differential Calculus on Persistence Barcodes , 2019, ArXiv.

[17]  Francis Bach,et al.  Learning with Differentiable Perturbed Optimizers , 2020, ArXiv.