Geometric Inference on Kernel Density Estimates

Authors Jeff M. Phillips, Bei Wang, Yan Zheng



PDF
Thumbnail PDF

File

LIPIcs.SOCG.2015.857.pdf
  • Filesize: 1.82 MB
  • 15 pages

Document Identifiers

Author Details

Jeff M. Phillips
Bei Wang
Yan Zheng

Cite AsGet BibTex

Jeff M. Phillips, Bei Wang, and Yan Zheng. Geometric Inference on Kernel Density Estimates. In 31st International Symposium on Computational Geometry (SoCG 2015). Leibniz International Proceedings in Informatics (LIPIcs), Volume 34, pp. 857-871, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
https://doi.org/10.4230/LIPIcs.SOCG.2015.857

Abstract

We show that geometric inference of a point cloud can be calculated by examining its kernel density estimate with a Gaussian kernel. This allows one to consider kernel density estimates, which are robust to spatial noise, subsampling, and approximate computation in comparison to raw point sets. This is achieved by examining the sublevel sets of the kernel distance, which isomorphically map to superlevel sets of the kernel density estimate. We prove new properties about the kernel distance, demonstrating stability results and allowing it to inherit reconstruction results from recent advances in distance-based topological reconstruction. Moreover, we provide an algorithm to estimate its topology using weighted Vietoris-Rips complexes.
Keywords
  • topological data analysis
  • kernel density estimate
  • kernel distance

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. N. Aronszajn. Theory of reproducing kernels. Transactions of the American Mathematical Society, 68:337-404, 1950. Google Scholar
  2. Sivaraman Balakrishnan, Brittany Terese Fasy, Fabrizio Lecci, Alessandro Rinaldo, Aarti Singh, and Larry Wasserman. Statistical inference for persistent homology. Technical report, ArXiv:1303.7117, March 2013. Google Scholar
  3. James Biagioni and Jakob Eriksson. Map inference in the face of noise and disparity. In ACM SIGSPATIAL GIS, 2012. Google Scholar
  4. Gérard Biau, Frédéric Chazal, David Cohen-Steiner, Luc Devroye, and Carlos Rodriguez. A weighted k-nearest neighbor density estimate for geometric inference. Electronic Journal of Statistics, 5:204-237, 2011. Google Scholar
  5. Omer Bobrowski, Sayan Mukherjee, and Jonathan E. Taylor. Topological consistency via kernel estimation. Technical report, arXiv:1407.5272, 2014. Google Scholar
  6. Peter Bubenik. Statistical topological data analysis using persistence landscapes. Jounral of Machine Learning Research, 2014. Google Scholar
  7. Mickael Buchet, Frederic Chazal, Steve Y. Oudot, and Donald R. Sheehy. Efficient and robust persistent homology for measures. In SODA, 2015. Google Scholar
  8. Frédéric Chazal and David Cohen-Steiner. Geometric inference. Tessellations in the Sciences, 2012. Google Scholar
  9. Frédéric Chazal, David Cohen-Steiner, Marc Glisse, Leonidas J. Guibas, and Steve Y. Oudot. Proximity of persistence modules and their diagrams. In SOCG, 2009. Google Scholar
  10. Frédéric Chazal, David Cohen-Steiner, and André Lieutier. Normal cone approximation and offset shape isotopy. CGTA, 42:566-581, 2009. Google Scholar
  11. Frédéric Chazal, David Cohen-Steiner, and André Lieutier. A sampling theory for compact sets in Euclidean space. DCG, 41(3):461-479, 2009. Google Scholar
  12. Frédéric Chazal, David Cohen-Steiner, and Quentin Mérigot. Geometric inference for probability measures. FOCM, 11(6):733-751, 2011. Google Scholar
  13. Frederic Chazal, Vin de Silva, Marc Glisse, and Steve Oudot. The structure and stability of persistence modules. arXiv:1207.3674, 2013. Google Scholar
  14. Frédéric Chazal, Brittany Terese Fasy, Fabrizio Lecci, Bertrand Michel, Alessandro Rinaldo, and Larry Wasserman. Robust topolical inference: Distance-to-a-measure and kernel distance. Technical report, arXiv:1412.7197, 2014. Google Scholar
  15. Frédéric Chazal, Brittany Terese Fasy, Fabrizio Lecci, Alessandro Rinaldo, Aarti Singh, and Larry Wasserman. On the bootstrap for persistence diagrams and landscapes. Modeling and Analysis of Information Systems, 20:96-105, 2013. Google Scholar
  16. Frédéric Chazal, Brittany Terese Fasy, Fabrizio Lecci, Alessandro Rinaldo, and Larry Wasserman. Stochastic convergence of persistence landscapes. In SOCG, 2014. Google Scholar
  17. Frédéric Chazal and André Lieutier. Weak feature size and persistent homology: computing homology of solids in Rⁿ from noisy data samples. In SOCG, pages 255-262, 2005. Google Scholar
  18. Frédéric Chazal and André Lieutier. Topology guaranteeing manifold reconstruction using distance function to noisy data. In SOCG, 2006. Google Scholar
  19. Frédéric Chazal and Steve Oudot. Towards persistence-based reconstruction in euclidean spaces. In SOCG, 2008. Google Scholar
  20. David Cohen-Steiner, Herbert Edelsbrunner, and John Harer. Stability of persistence diagrams. DCG, 37:103-120, 2007. Google Scholar
  21. Luc Devroye and László Györfi. Nonparametric Density Estimation: The L₁ View. Wiley, 1984. Google Scholar
  22. Luc Devroye and Gábor Lugosi. Combinatorial Methods in Density Estimation. Springer-Verlag, 2001. Google Scholar
  23. Herbert Edelsbrunner. The union of balls and its dual shape. In SOCG, 1993. Google Scholar
  24. Herbert Edelsbrunner, Michael Facello, Ping Fu, and Jie Liang. Measuring proteins and voids in proteins. In Proceedings 28th Annual Hawaii International Conference on Systems Science, 1995. Google Scholar
  25. Herbert Edelsbrunner, Brittany Terese Fasy, and Günter Rote. Add isotropic Gaussian kernels at own risk: More and more resiliant modes in higher dimensions. In SOCG, 2012. Google Scholar
  26. Herbert Edelsbrunner and John Harer. Persistent homology. Contemporary Mathematics, 453:257-282, 2008. Google Scholar
  27. Herbert Edelsbrunner and John Harer. Computational Topology: An Introduction. American Mathematical Society, Providence, RI, USA, 2010. Google Scholar
  28. Ahmed Elgammal, Ramani Duraiswami, David Harwood, and Larry S. Davis. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proc. IEEE, 90:1151-1163, 2002. Google Scholar
  29. Brittany Terese Fasy, Jisu Kim, Fabrizio Lecci, and Clément Maria. Introduction to the R package TDA. Technical report, arXiV:1411.1830, 2014. Google Scholar
  30. Brittany Terese Fasy, Fabrizio Lecci, Alessandro Rinaldo, Larry Wasserman, Sivaraman Balakrishnan, and Aarti Singh. Statistical inference for persistent homology: Confidence sets for persistence diagrams. In The Annals of Statistics, volume 42, pages 2301-2339, 2014. Google Scholar
  31. H. Federer. Curvature measures. Transactions of the American Mathematical Society, 93:418-491, 1959. Google Scholar
  32. Mingchen Gao, Chao Chen, Shaoting Zhang, Zhen Qian, Dimitris Metaxas, and Leon Axel. Segmenting the papillary muscles and the trabeculae from high resolution cardiac CT through restoration of topological handles. In Proceedings International Conference on Information Processing in Medical Imaging, 2013. Google Scholar
  33. Joan Glaunès. Transport par difféomorphismes de points, de mesures et de courants pour la comparaison de formes et l'anatomie numérique. PhD thesis, Université Paris 13, 2005. Google Scholar
  34. Karsten Grove. Critical point theory for distance functions. Proceedings of Symposia in Pure Mathematics, 54:357-385, 1993. Google Scholar
  35. Leonidas Guibas, Quentin Mérigot, and Dmitriy Morozov. Witnessed k-distance. In SOCG, 2011. Google Scholar
  36. Allen Hatcher. Algebraic Topology. Cambridge University Press, 2002. Google Scholar
  37. Matrial Hein and Olivier Bousquet. Hilbertian metrics and positive definite kernels on probability measures. In Proceedings 10th International Workshop on Artificial Intelligence and Statistics, 2005. Google Scholar
  38. Sarang Joshi, Raj Varma Kommaraju, Jeff M. Phillips, and Suresh Venkatasubramanian. Comparing distributions and shapes using the kernel distance. In SOCG, 2011. Google Scholar
  39. John M. Lee. Introduction to smooth manifolds. Springer, 2003. Google Scholar
  40. Jie Liang, Herbert Edelsbrunner, Ping Fu, Pamidighantam V. Sudharkar, and Shankar Subramanian. Analytic shape computation of macromolecues: I. molecular area and volume through alpha shape. Proteins: Structure, Function, and Genetics, 33:1-17, 1998. Google Scholar
  41. André Lieutier. Any open bounded subset of ℝⁿ has the same homotopy type as its medial axis. Computer-Aided Design, 36:1029-1046, 2004. Google Scholar
  42. Quentin Mérigot. Geometric structure detection in point clouds. PhD thesis, Université de Nice Sophia-Antipolis, 2010. Google Scholar
  43. Yuriy Mileyko, Sayan Mukherjee, and John Harer. Probability measures on the space of persistence diagrams. Inverse Problems, 27(12), 2011. Google Scholar
  44. A. Müller. Integral probability metrics and their generating classes of functions. Advances in Applied Probability, 29(2):429-443, 1997. Google Scholar
  45. Jeff M. Phillips. ε-samples for kernels. SODA, 2013. Google Scholar
  46. Jeff M. Phillips and Suresh Venkatasubramanian. A gentle introduction to the kernel distance. arXiv:1103.1625, March 2011. Google Scholar
  47. Jeff M. Phillips, Bei Wang, and Yan Zheng. Geometric inference on kernel density estimates. In arXiv:1307.7760, 2015. Google Scholar
  48. Florian T. Pokorny, Carl Henrik, Hedvig Kjellström, and Danica Kragic. Persistent homology for learning densities with bounded support. In Neural Informations Processing Systems, 2012. Google Scholar
  49. Charles A. Price, Olga Symonova, Yuriy Mileyko, Troy Hilley, and Joshua W. Weitz. Leaf gui: Segmenting and analyzing the structure of leaf veins and areoles. Plant Physiology, 155:236-245, 2011. Google Scholar
  50. David W. Scott. Multivariate Density Estimation: Theory, Practice, and Visualization. Wiley, 1992. Google Scholar
  51. Donald R. Sheehy. A multicover nerve for geometric inference. CCCG, 2012. Google Scholar
  52. Bernard W. Silverman. Using kernel density esimates to inversitigate multimodality. J. R. Sratistical Society B, 43:97-99, 1981. Google Scholar
  53. Bernard W. Silverman. Density Estimation for Statistics and Data Analysis. Chapman & Hall/CRC, 1986. Google Scholar
  54. Bharath K. Sriperumbudur, Arthur Gretton, Kenji Fukumizu, Bernhard Schölkopf, and Gert R. G. Lanckriet. Hilbert space embeddings and metrics on probability measures. JMLR, 11:1517-1561, 2010. Google Scholar
  55. Kathryn Turner, Yuriy Mileyko, Sayan Mukherjee, and John Harer. Fréchet means for distributions of persistence diagrams. DCG, 2014. Google Scholar
  56. Cédric Villani. Topics in Optimal Transportation. American Mathematical Society, 2003. Google Scholar
  57. Grace Wahba. Support vector machines, reproducing kernel Hilbert spaces, and randomization. In Advances in Kernel Methods - Support Vector Learning, pages 69-88. The MIT Press, 1999. Google Scholar
  58. Yan Zheng, Jeffrey Jestes, Jeff M. Phillips, and Feifei Li. Quality and efficiency in kernel density estimates for large data. In SIGMOD, 2012. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail