Simplified and Improved Bounds on the VC-Dimension for Elastic Distance Measures
Abstract: We study range spaces, where the ground set consists of either polygonal curves in $\mathbb{R}d$ or polygonal regions in the plane that may contain holes and the ranges are balls defined by an elastic distance measure, such as the Hausdorff distance, the Fr\'echet distance and the dynamic time warping distance. The range spaces appear in various applications like classification, range counting, density estimation and clustering when the instances are trajectories, time series or polygons. The Vapnik-Chervonenkis dimension (VC-dimension) plays an important role when designing algorithms for these range spaces. We show for the Fr\'echet distance of polygonal curves and the Hausdorff distance of polygonal curves and planar polygonal regions that the VC-dimension is upper-bounded by $O(dk\log(km))$ where $k$ is the complexity of the center of a ball, $m$ is the complexity of the polygonal curve or region in the ground set, and $d$ is the ambient dimension. For $d \geq 4$ this bound is tight in each of the parameters $d, k$ and $m$ separately. For the dynamic time warping distance of polygonal curves, our analysis directly yields an upper-bound of $O(\min(dk2\log(m),dkm\log(k)))$.
- On the complexity of range searching among curves. In Proceedings of the 2018 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pages 898–917, 2018.
- Subtrajectory Clustering: Finding Set Covers for Set Systems of Subcurves. Computing in Geometry and Topology, 2(1):1:1–1:48, Feb. 2023.
- Neural Network Learning: Theoretical Foundations. Cambridge University Press, 1999.
- Localization vs. Identification of Semi-Algebraic Sets. In Lenny Pitt, editor, Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, COLT 1993, Santa Cruz, CA, USA, July 26-28, 1993, pages 327–336. ACM, 1993.
- Faster Approximate Covering of Subcurves Under the Fréchet Distance. In Shiri Chechik, Gonzalo Navarro, Eva Rotenberg, and Grzegorz Herman, editors, 30th Annual European Symposium on Algorithms (ESA 2022), volume 244 of Leibniz International Proceedings in Informatics (LIPIcs), pages 28:1–28:16, Dagstuhl, Germany, 2022. Schloss Dagstuhl – Leibniz-Zentrum für Informatik.
- Coresets for (k,ℓ𝑘ℓk,\ellitalic_k , roman_ℓ)-Median Clustering Under the Fréchet Distance. In Niranjan Balachandran and R. Inkulu, editors, Algorithms and Discrete Applied Mathematics, pages 167–180, Cham, 2022. Springer International Publishing.
- Solving Fréchet distance problems by algebraic geometric methods. CoRR, abs/2308.14569, 2023.
- Solving Fréchet distance problems by algebraic geometric methods. In Proceedings of the 2024 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2024. To appear.
- The VC Dimension of Metric Balls under Fréchet and Hausdorff Distances. Discrete & Computational Geometry, 66(4):1351–1381, 2021.
- Dan Feldman. Introduction to Core-sets: an Updated Survey. ArXiv, abs/2011.09384, 2020.
- A Unified Framework for Approximating and Clustering Data. In Proceedings of the Forty-Third Annual ACM Symposium on Theory of Computing, STOC ’11, page 569–578, New York, NY, USA, 2011. Association for Computing Machinery.
- Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers. In Lenny Pitt, editor, Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, COLT 1993, Santa Cruz, CA, USA, July 26-28, 1993, pages 361–369. ACM, 1993.
- Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers. Machine Learning, 18:131–148, 1995.
- Relative (p, ϵitalic-ϵ\epsilonitalic_ϵ)-Approximations in Geometry. Discret. Comput. Geom., 45(3):462–496, 2011.
- Epsilon-nets and simplex range queries. Discrete & Computational Geometry, 2(2):127–151, 1987.
- Comparing Distributions and Shapes Using the Kernel Distance. In Proceedings of the Twenty-Seventh Annual Symposium on Computational Geometry, SoCG ’11, page 47–56, New York, NY, USA, 2011. Association for Computing Machinery.
- Polynomial bounds for VC dimension of sigmoidal neural networks. In Proceedings of the Twenty-Seventh Annual ACM Symposium on Theory of Computing, STOC ’95, page 200–208, New York, NY, USA, 1995. Association for Computing Machinery.
- Applying VC-dimension analysis to 3D object recognition from perspective projections. In Barbara Hayes-Roth and Richard E. Korf, editors, Proceedings of the 12th National Conference on Artificial Intelligence, Seattle, WA, USA, July 31 - August 4, 1994, Volume 2, pages 985–990. AAAI Press / The MIT Press, 1994.
- Applying VC-dimension analysis to object recognition. In Jan-Olof Eklundh, editor, Computer Vision - ECCV’94, Third European Conference on Computer Vision, Stockholm, Sweden, May 2-6, 1994, Proceedings, Volume I, volume 800 of Lecture Notes in Computer Science, pages 239–250. Springer, 1994.
- Vladimir N. Vapnik. The Nature of Statistical Learning Theory. Springer New York, NY, 2000.
- On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability & Its Applications, 16(2):264–280, 1971.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.