Papers
Topics
Authors
Recent
Search
2000 character limit reached

Generalized Dimension Reduction Using Semi-Relaxed Gromov-Wasserstein Distance

Published 24 May 2024 in math.OC and math.MG | (2405.15959v3)

Abstract: Dimension reduction techniques typically seek an embedding of a high-dimensional point cloud into a low-dimensional Euclidean space which optimally preserves the geometry of the input data. Based on expert knowledge, one may instead wish to embed the data into some other manifold or metric space in order to better reflect the geometry or topology of the point cloud. We propose a general method for manifold-valued multidimensional scaling based on concepts from optimal transport. In particular, we establish theoretical connections between the recently introduced semi-relaxed Gromov-Wasserstein (srGW) framework and multidimensional scaling by solving the Monge problem in this setting. We also derive novel connections between srGW distance and Gromov-Hausdorff distance. We apply our computational framework to analyze ensembles of political redistricting plans for states with two Congressional districts, achieving an effective visualization of the ensemble as a distribution on a circle which can be used to characterize typical neutral plans, and to flag outliers.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Geometry of graph partitions via optimal transport. SIAM Journal on Scientific Computing, 42(5):A3340–A3366, 2020.
  2. The Gromov-Wasserstein distance between spheres. arXiv preprint arXiv:2306.10586, 2023.
  3. Assessing congressional districting in maine and new hampshire. arXiv preprint arXiv:2011.06555, 2020.
  4. On assignment problems related to Gromov–Wasserstein distances on the real line. SIAM Journal on Imaging Sciences, 16(2):1028–1032, 2023.
  5. Yann Brenier. Décomposition polaire et réarrangement monotone des champs de vecteurs. CR Acad. Sci. Paris Sér. I Math., 305:805–808, 1987.
  6. Generalized multidimensional scaling: a framework for isometry-invariant partial surface matching. Proceedings of the National Academy of Sciences, 103(5):1168–1172, 2006.
  7. A course in metric geometry, volume 33. American Mathematical Society, 2022.
  8. Cutting through the thicket: Redistricting simulations and the detection of partisan gerrymanders. Election Law Journal, 14(4):331–345, 2015.
  9. Assessing significance in a markov chain without mixing. Proceedings of the National Academy of Sciences, 114(11):2860–2864, 2017.
  10. Quantized Gromov-Wasserstein. In Machine Learning and Knowledge Discovery in Databases. Research Track: European Conference, ECML PKDD 2021, Bilbao, Spain, September 13–17, 2021, Proceedings, Part III 21, pages 811–827. Springer, 2021.
  11. Generalized spectral clustering via Gromov-Wasserstein learning. In International Conference on Artificial Intelligence and Statistics, pages 712–720. PMLR, 2021.
  12. Hypergraph co-optimal transport: Metric and categorical properties. Journal of Applied and Computational Topology, pages 1–60, 2023.
  13. Persistent cohomology and circular coordinates. In Proceedings of the twenty-fifth annual symposium on Computational geometry, pages 227–236, 2009.
  14. Recombination: A family of markov chains for redistricting. Harvard Data Science Review, 3(1):3, 2021.
  15. On the existence of monge maps for the Gromov–Wasserstein problem. Foundations of Computational Mathematics, pages 1–48, 2024.
  16. Pot: Python optimal transport. Journal of Machine Learning Research, 22(78):1–8, 2021.
  17. Quantifying gerrymandering in north carolina. Statistics and Public Policy, 7(1):30–38, 2020.
  18. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  19. Ipums national historical geographic information system: Version 18.0 [dataset]. http://doi.org/10.18128/D050.V18.0, 2023.
  20. Facundo Memoli. On the use of Gromov-Hausdorff Distances for Shape Comparison. In M. Botsch, R. Pajarola, B. Chen, and M. Zwicker, editors, Eurographics Symposium on Point-Based Graphics. The Eurographics Association, 2007.
  21. Facundo Mémoli. Gromov–Wasserstein distances and the metric approach to object matching. Foundations of computational mathematics, 11:417–487, 2011.
  22. Facundo Mémoli. Some properties of Gromov–Hausdorff distances. Discrete & Computational Geometry, 48:416–440, 2012.
  23. The ultrametric Gromov-Wasserstein distance. Discrete & Computational Geometry, 70:1378–1450, 2023.
  24. Comparison results for Gromov-Wasserstein and Gromov-monge distances. arXiv preprint arXiv:2212.14123, 2022.
  25. Distance distributions and inverse problems for metric measure spaces. Studies in Applied Mathematics, 149(4):943–1001, 2022.
  26. Circular coordinates for density-robust analysis. arXiv preprint arXiv:2301.12742, 2023.
  27. Jose A Perea. Multiscale projective coordinates via persistent cohomology of sparse filtrations. Discrete & Computational Geometry, 59:175–225, 2018.
  28. Gromov-Wasserstein averaging of kernel and distance matrices. In International conference on machine learning, pages 2664–2672. PMLR, 2016.
  29. Coordinatizing data with lens spaces and persistent cohomology. In Proceedings of the 31 st Canadian Conference on Computational Geometry (CCCG), pages 49–57, 2019.
  30. Compact redistricting plans have many spanning trees. In Proceedings of the 2022 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pages 3754–3771. SIAM, 2022.
  31. Gromov-Wasserstein distances between gaussian distributions. Journal of Applied Probability, 59(4), 2022.
  32. Linear-time Gromov Wasserstein distances using low rank couplings and costs. In International Conference on Machine Learning, pages 19347–19365. PMLR, 2022.
  33. Karl-Theodor Sturm. The Space of Spaces: Curvature Bounds and Gradient Flows on the Space of Metric Measure Spaces, volume 290. American Mathematical Society, 2023.
  34. Co-optimal transport. Advances in neural information processing systems, 33:17559–17570, 2020.
  35. Distributional reduction: Unifying dimensionality reduction and clustering with Gromov-Wasserstein projection. arXiv preprint arXiv:2402.02239, 2024.
  36. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
  37. Titouan Vayer. A contribution to optimal transport on incomparable spaces. arXiv preprint arXiv:2011.04447, 2020.
  38. Fused Gromov-Wasserstein distance for structured objects. Algorithms, 13(9):212, 2020.
  39. Cédric Villani. Topics in optimal transportation, volume 58. American Mathematical Soc., 2021.
  40. Cédric Villani et al. Optimal transport: old and new, volume 338. Springer, 2009.
  41. Semi-relaxed Gromov Wasserstein divergence with applications on graphs. In International Conference on Learning Representations, 2022.
  42. Scalable Gromov-Wasserstein learning for graph partitioning and matching. Advances in neural information processing systems, 32, 2019.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 2 tweets with 1 like about this paper.

Sign Up for Free