Document Open Access Logo

Tight Bounds for the Learning of Homotopy à la Niyogi, Smale, and Weinberger for Subsets of Euclidean Spaces and of Riemannian Manifolds

Authors Dominique Attali, Hana Dal Poz Kouřimská , Christopher Fillmore , Ishika Ghosh , André Lieutier, Elizabeth Stephenson , Mathijs Wintraecken

PDF
Thumbnail PDF

File

LIPIcs.SoCG.2024.11.pdf
  • Filesize: 19.91 MB
  • 19 pages

Document Identifiers

Author Details

Dominique Attali
  • Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab, Grenoble, France
Hana Dal Poz Kouřimská
  • IST Austria, Klosterneuburg, Austria
Christopher Fillmore
  • IST Austria, Klosterneuburg, Austria
Ishika Ghosh
  • IST Austria, Klosterneuburg, Austria
  • Michigan State University, East Lansing, MI, USA
André Lieutier
  • Aix-en-Provence, France
Elizabeth Stephenson
  • IST Austria, Klosterneuburg, Austria
Mathijs Wintraecken
  • Inria Sophia Antipolis, Université Côte d'Azur, Sophia Antipolis, France

Funding

This research has been supported by the European Research Council (ERC), grant No. 788183, by the Wittgenstein Prize, Austrian Science Fund (FWF), grant No. Z 342-N31, and by the DFG Collaborative Research Center TRR 109, Austrian Science Fund (FWF), grant No. I 02979-N35.
  • Wintraecken, Mathijs: Supported by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 754411, the Austrian science fund (FWF) grant No. M-3073, and the welcome package from IDEX of the Université Côte d'Azur.

Acknowledgements

We thank Jean-Daniel Boissonnat, Herbert Edelsbrunner, and Mariette Yvinec for discussion.

Cite AsGet BibTex

Dominique Attali, Hana Dal Poz Kouřimská, Christopher Fillmore, Ishika Ghosh, André Lieutier, Elizabeth Stephenson, and Mathijs Wintraecken. Tight Bounds for the Learning of Homotopy à la Niyogi, Smale, and Weinberger for Subsets of Euclidean Spaces and of Riemannian Manifolds. In 40th International Symposium on Computational Geometry (SoCG 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 293, pp. 11:1-11:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
https://doi.org/10.4230/LIPIcs.SoCG.2024.11

Abstract

In this article we extend and strengthen the seminal work by Niyogi, Smale, and Weinberger on the learning of the homotopy type from a sample of an underlying space. In their work, Niyogi, Smale, and Weinberger studied samples of C² manifolds with positive reach embedded in ℝ^d. We extend their results in the following ways: - As the ambient space we consider both ℝ^d and Riemannian manifolds with lower bounded sectional curvature. - In both types of ambient spaces, we study sets of positive reach - a significantly more general setting than C² manifolds - as well as general manifolds of positive reach. - The sample P of a set (or a manifold) 𝒮 of positive reach may be noisy. We work with two one-sided Hausdorff distances - ε and δ - between P and 𝒮. We provide tight bounds in terms of ε and δ, that guarantee that there exists a parameter r such that the union of balls of radius r centred at the sample P deformation-retracts to 𝒮. We exhibit their tightness by an explicit construction. We carefully distinguish the roles of δ and ε. This is not only essential to achieve tight bounds, but also sensible in practical situations, since it allows one to adapt the bound according to sample density and the amount of noise present in the sample separately.

Subject Classification

ACM Subject Classification
  • Theory of computation → Computational geometry
Keywords
  • Homotopy
  • Inference
  • Sets of positive reach

Metrics

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

Related Versions

References

  1. Eddie Aamari, Catherine Aaron, and Clément Levrard. Minimax boundary estimation and estimation with boundary, 2021. URL: https://doi.org/10.48550/arXiv.2108.03135.
  2. Eddie Aamari, Clément Berenfeld, and Clément Levrard. Optimal reach estimation and metric learning, 2022. URL: https://doi.org/10.48550/arXiv.2207.06074.
  3. Eddie Aamari, Jisu Kim, Frédéric Chazal, Bertrand Michel, Alessandro Rinaldo, and Larry Wasserman. Estimating the reach of a manifold. Electronic Journal of Statistics, 13(1):1359-1399, 2019. URL: https://doi.org/10.1214/19-EJS1551.
  4. Eddie Aamari and Alexander Knop. Statistical query complexity of manifold estimation. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, STOC 2021, pages 116-122, New York, NY, USA, 2021. Association for Computing Machinery. URL: https://doi.org/10.1145/3406325.3451135.
  5. Eddie Aamari and Clément Levrard. Stability and minimax optimality of tangential Delaunay complexes for manifold reconstruction. Discrete & Computational Geometry, 59:923-971, 2018. Google Scholar
  6. Michał Adamaszek and Henry Adams. The Vietoris-Rips complexes of a circle. Pacific Journal of Mathematics, 290(1):1-40, 2017. Google Scholar
  7. Michał Adamaszek, Henry Adams, and Samadwara Reddy. On Vietoris-Rips complexes of ellipses. Journal of Topology and Analysis, 11(03):661-690, 2019. URL: https://doi.org/10.1142/S1793525319500274.
  8. Paolo Albano and Piermarco Cannarsa. Structural properties of singularities of semiconcave functions. Annali della Scuola Normale Superiore di Pisa-Classe di Scienze, 28(4):719-740, 1999. Google Scholar
  9. Paolo Albano, Piermarco Cannarsa, Khai T Nguyen, and Carlo Sinestrari. Singular gradient flow of the distance function and homotopy equivalence. Mathematische Annalen, 356(1):23-43, 2013. Google Scholar
  10. Nina Amenta, Sunghee Choi, Tamal K Dey, and Naveen Leekha. A simple algorithm for homeomorphic surface reconstruction. In Proceedings of the sixteenth annual symposium on Computational geometry, pages 213-222, 2000. Google Scholar
  11. Aleksander Antasik. Sampling C¹-submanifolds of ℍⁿ. In Colloquium Mathematicum, volume 168, pages 211-228. Instytut Matematyczny Polskiej Akademii Nauk, 2022. Google Scholar
  12. Dominique Attali, Hana Dal Poz Kouřimská, Christopher Fillmore, Ishika Ghosh, André Lieutier, Elizabeth Stephenson, and Mathijs Wintraecken. The ultimate frontier: An optimality construction for homotopy inference. In Xavier Goaoc and Michael Kerber, editors, Medial exposition 40th International Symposium on Computational Geometry (SoCG 2024), Leibniz International Proceedings in Informatics (LIPIcs), Dagstuhl, Germany, 2024. Schloss Dagstuhl - Leibniz-Zentrum für Informatik. Google Scholar
  13. Dominique Attali, Hana Dal Poz Kouřimská, Christopher Fillmore, Ishika Ghosh, André Lieutier, Elizabeth Stephenson, and Mathijs Wintraecken. Tight bounds for the learning of homotopy à la niyogi, smale, and weinberger for subsets of euclidean spaces and of riemannian manifolds. arXiv preprint, 2024. URL: https://arxiv.org/abs/2206.10485.
  14. Dominique Attali and André Lieutier. Reconstructing shapes with guarantees by unions of convex sets. 33 pages, December 2009. URL: https://hal.archives-ouvertes.fr/hal-00427035v2.
  15. Dominique Attali, André Lieutier, and David Salinas. Vietoris-rips complexes also provide topologically correct reconstructions of sampled shapes. Computational Geometry, 46(4):448-465, 2013. 27th Annual Symposium on Computational Geometry (SoCG 2011). URL: https://doi.org/10.1016/j.comgeo.2012.02.009.
  16. Victor Bangert. Sets with positive reach. Archiv der Mathematik, 38(1):54-57, 1982. Google Scholar
  17. Clément Berenfeld, John Harvey, Marc Hoffmann, and Krishnan Shankar. Estimating the reach of a manifold via its convexity defect function. Discrete & Computational Geometry, 67(2):403-438, 2022. Google Scholar
  18. Marcel Berger. A panoramic view of Riemannian geometry. Springer, 2003. Google Scholar
  19. Matthew Berger, Andrea Tagliasacchi, Lee M Seversky, Pierre Alliez, Gael Guennebaud, Joshua A Levine, Andrei Sharf, and Claudio T Silva. A survey of surface reconstruction from point clouds. In Computer Graphics Forum, volume 36, pages 301-329. Wiley Online Library, 2017. Google Scholar
  20. Anders Björner. Topological methods. handbook of combinatorics, vol. 1, 2, 1819-1872, 1995. Google Scholar
  21. Jean-Daniel Boissonnat. Geometric structures for three-dimensional shape representation. ACM Transactions on Graphics (TOG), 3(4):266-286, 1984. Google Scholar
  22. Jean-Daniel Boissonnat. Shape reconstruction from planar cross sections. Computer vision, graphics, and image processing, 44(1):1-29, 1988. Google Scholar
  23. Jean-Daniel Boissonnat, Frédéric Chazal, and Mariette Yvinec. Geometric and Topological Inference. Cambridge Texts in Applied Mathematics. Cambridge University Press, 2018. URL: https://doi.org/10.1017/9781108297806.
  24. Jean-Daniel Boissonnat and Mathijs Wintraecken. The reach of subsets of manifolds. Journal of Applied and Computational Topology, pages 1-23, 2023. Google Scholar
  25. P. Buser and H. Karcher. Gromov’s almost flat manifolds, volume 81 of Astérique. Société mathématique de France, 1981. Google Scholar
  26. Isaac Chavel. Riemannian geometry: a modern introduction, volume 98. Cambridge university press, 2006. Google Scholar
  27. F. Chazal, D. Cohen-Steiner, and A. Lieutier. A sampling theory for compact sets in Euclidean space. Discrete and Computational Geometry, 41(3):461-479, 2009. Google Scholar
  28. F. Chazal and A. Lieutier. The λ-medial axis. Graphical Models, 67(4):304-331, 2005. Google Scholar
  29. Frédéric Chazal, David Cohen-Steiner, and Quentin Mérigot. Geometric inference for measures based on distance functions. Foundations of computational mathematics, 11(6):733-751, 2011. Google Scholar
  30. Frédéric Chazal, Leonidas J Guibas, Steve Y Oudot, and Primoz Skraba. Persistence-based clustering in Riemannian manifolds. Journal of the ACM (JACM), 60(6):1-38, 2013. Google Scholar
  31. Frédéric Chazal and André Lieutier. Weak feature size and persistent homology: computing homology of solids in ℝⁿ from noisy data samples. In Proceedings of the twenty-first annual symposium on Computational geometry, pages 255-262, 2005. Google Scholar
  32. Frédéric Chazal and André Lieutier. Smooth manifold reconstruction from noisy and non-uniform approximation with guarantees. Computational Geometry, 40(2):156-170, 2008. Google Scholar
  33. Frédéric Chazal and Steve Yann Oudot. Towards persistence-based reconstruction in Euclidean spaces. In Proceedings of the twenty-fourth annual symposium on Computational geometry, pages 232-241, 2008. Google Scholar
  34. Jeff Cheeger and David G. Ebin. Comparison Theorems in Riemannian Geometry, volume 365. American Mathematical Soc., 2008. Google Scholar
  35. Alejandro Cholaquidis, Ricardo Fraiman, and Leonardo Moreno. Universally consistent estimation of the reach. Journal of Statistical Planning and Inference, 225:110-120, 2023. Google Scholar
  36. Frank H. Clarke. Optimization and Nonsmooth Analysis, volume 5 of Classics in applied mathematics. SIAM, 1990. Google Scholar
  37. Ryan Cotsakis. Computable bounds for the reach and r-convexity of subsets of r d. Discrete & Computational Geometry, pages 1-37, 2024. Google Scholar
  38. Tamal Krishna Dey and Yusu Wang. Computational topology for data analysis. Cambridge University Press, 2022. Google Scholar
  39. Herbert Edelsbrunner. Alpha shapes-a survey. In Tessellations in the Sciences: Virtues, Techniques and Applications of Geometric Tilings. Springer, 2011. Google Scholar
  40. Herbert Edelsbrunner and John Harer. Computational topology: an introduction. American Mathematical Soc., 2010. Google Scholar
  41. Herbert Edelsbrunner and Nimish R Shah. Triangulating topological spaces. In Proceedings of the tenth annual symposium on Computational geometry, pages 285-292, 1994. Google Scholar
  42. H. Federer. Curvature measures. Transactions of the America mathematical Society, 93:418-491, 1959. Google Scholar
  43. Charles Fefferman, Sergei Ivanov, Yaroslav Kurylev, Matti Lassas, and Hariharan Narayanan. Fitting a putative manifold to noisy data. In Conference On Learning Theory, pages 688-720. PMLR, 2018. Google Scholar
  44. Charles Fefferman, Sergei Ivanov, Matti Lassas, and Hariharan Narayanan. Fitting a manifold of large reach to noisy data. arXiv preprint, 2019. URL: https://arxiv.org/abs/1910.05084.
  45. Charles Fefferman, Sergei Ivanov, Matti Lassas, and Hariharan Narayanan. Reconstruction of a Riemannian manifold from noisy intrinsic distances. SIAM Journal on Mathematics of Data Science, 2(3):770-808, 2020. Google Scholar
  46. Alvina Goh and René Vidal. Clustering and dimensionality reduction on Riemannian manifolds. In 2008 IEEE Conference on computer vision and pattern recognition, pages 1-7. IEEE, 2008. Google Scholar
  47. Detlef Gromoll, Wilhelm Klingenberg, and Wolfgang Meyer. Riemannsche Geometrie im Großen. Lecture Notes in Mathematics. Springer, 1975. URL: https://doi.org/10.1007/BFb0079185.
  48. Jihun Hamm and Daniel D Lee. Grassmann discriminant analysis: a unifying view on subspace-based learning. In Proceedings of the 25th international conference on Machine learning, pages 376-383, 2008. Google Scholar
  49. Mehrtash T Harandi, Conrad Sanderson, Sareh Shirazi, and Brian C Lovell. Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching. In CVPR 2011, pages 2705-2712. IEEE, 2011. Google Scholar
  50. Jean-Claude Hausmann et al. On the Vietoris-Rips complexes and a cohomology theory for metric spaces. Annals of Mathematics Studies, 138:175-188, 1995. Google Scholar
  51. H. Karcher. Riemannian comparison constructions. In S.S. Chern, editor, Global Differential Geometry, pages 170-222. The mathematical association of America, 1989. Google Scholar
  52. Jisu Kim, Jaehyeok Shin, Frédéric Chazal, Alessandro Rinaldo, and Larry Wasserman. Homotopy Reconstruction via the Cech Complex and the Vietoris-Rips Complex. In Sergio Cabello and Danny Z. Chen, editors, 36th International Symposium on Computational Geometry (SoCG 2020), volume 164 of Leibniz International Proceedings in Informatics (LIPIcs), pages 54:1-54:19, Dagstuhl, Germany, 2020. Schloss Dagstuhl-Leibniz-Zentrum für Informatik. URL: https://doi.org/10.4230/LIPIcs.SoCG.2020.54.
  53. Norbert Kleinjohann. Convexity and the unique footpoint property in Riemannian geometry. Archiv der Mathematik, 35(1):574-582, 1980. Google Scholar
  54. Norbert Kleinjohann. Nächste Punkte in der Riemannschen Geometrie. Mathematische Zeitschrift, 176(3):327-344, 1981. Google Scholar
  55. Janko Latschev. Vietoris-Rips complexes of metric spaces near a closed Riemannian manifold. Archiv der Mathematik, 77(6):522-528, 2001. Google Scholar
  56. David Levin. The approximation power of moving least-squares. Mathematics of computation, 67(224):1517-1531, 1998. Google Scholar
  57. André Lieutier. Any open bounded subset of ℝⁿ has the same homotopy type as its medial axis. Computer-Aided Design, 36(11):1029-1046, 2004. Solid Modeling Theory and Applications. URL: https://doi.org/10.1016/j.cad.2004.01.011.
  58. Alexander Lytchak. On the geometry of subsets of positive reach. manuscripta mathematica, 115(2):199-205, 2004. Google Scholar
  59. Alexander Lytchak. Almost convex subsets. Geometriae Dedicata, 115(1):201-218, 2005. Google Scholar
  60. P. Niyogi, S. Smale, and S. Weinberger. Finding the homology of submanifolds with high confidence from random samples. Discrete & Computational Geometry, 39(1-3):419-441, 2008. Google Scholar
  61. Xavier Pennec, Pierre Fillard, and Nicholas Ayache. A Riemannian framework for tensor computing. International Journal of computer vision, 66:41-66, 2006. Google Scholar
  62. Robert Pless and Richard Souvenir. A survey of manifold learning for images. IPSJ Transactions on Computer Vision and Applications, 1:83-94, 2009. Google Scholar
  63. Jan Rataj and Martina Zähle. Curvature measures of singular sets. Springer, 2019. Google Scholar
  64. Jan Rataj and Luděk Zajíček. On the structure of sets with positive reach. Mathematische Nachrichten, 290(11-12):1806-1829, 2017. URL: https://doi.org/10.1002/mana.201600237.
  65. Yogesh Rathi, Allen Tannenbaum, and Oleg Michailovich. Segmenting images on the tensor manifold. In 2007 IEEE Conference on Computer Vision and Pattern Recognition, pages 1-8. IEEE, 2007. Google Scholar
  66. Barak Sober and David Levin. Manifold approximation by moving least-squares projection (MMLS). Constructive Approximation, 52(3):433-478, 2020. Google Scholar
  67. Oncel Tuzel, Fatih Porikli, and Peter Meer. Region covariance: A fast descriptor for detection and classification. In Computer Vision-ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part II 9, pages 589-600. Springer, 2006. Google Scholar
  68. Raviteja Vemulapalli and David W Jacobs. Riemannian metric learning for symmetric positive definite matrices. arXiv preprint, 2015. URL: https://arxiv.org/abs/1501.02393.
  69. Yuan Wang and Bei Wang. Topological inference of manifolds with boundary. Computational Geometry, 88:101606, 2020. URL: https://doi.org/10.1016/j.comgeo.2019.101606.
  70. Xikang Zhang, Yin Wang, Mengran Gou, Mario Sznaier, and Octavia Camps. Efficient temporal sequence comparison and classification using gram matrix embeddings on a riemannian manifold. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4498-4507, 2016. Google Scholar
  71. Pengfei Zhu, Hao Cheng, Qinghua Hu, Qilong Wang, and Changqing Zhang. Towards generalized and efficient metric learning on riemannian manifold. In International Joint Conference on Artificial Intelligence, pages 3235-3241, 2018. 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
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact