Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
12 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Horospherical Decision Boundaries for Large Margin Classification in Hyperbolic Space (2302.06807v3)

Published 14 Feb 2023 in stat.ML and cs.LG

Abstract: Hyperbolic spaces have been quite popular in the recent past for representing hierarchically organized data. Further, several classification algorithms for data in these spaces have been proposed in the literature. These algorithms mainly use either hyperplanes or geodesics for decision boundaries in a large margin classifiers setting leading to a non-convex optimization problem. In this paper, we propose a novel large margin classifier based on horospherical decision boundaries that leads to a geodesically convex optimization problem that can be optimized using any Riemannian gradient descent technique guaranteeing a globally optimal solution. We present several experiments depicting the competitive performance of our classifier in comparison to SOTA.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Optimization algorithms on matrix manifolds. In Optimization Algorithms on Matrix Manifolds. Princeton University Press, 2009.
  2. The political blogosphere and the 2004 us election: divided they blog. In Proceedings of the 3rd international workshop on Link discovery, pages 36–43, 2005.
  3. Pattern recognition and machine learning, volume 4. Springer, 2006.
  4. Roberto Bonola. Non-Euclidean geometry: A critical and historical study of its development. Courier Corporation, 1955.
  5. Nicolas Boumal. An introduction to optimization on smooth manifolds. Available online, May, 3, 2020.
  6. Metric spaces of non-positive curvature, volume 319. Springer Science & Business Media, 2013.
  7. Hyperbolic Geometry, volume 31. MSRI Publications, 1997.
  8. Neural embeddings of graphs in hyperbolic space. arXiv preprint arXiv:1705.10359, 2017.
  9. Horopca: Hyperbolic dimensionality reduction via horospherical projections. In International Conference on Machine Learning, pages 1419–1429. PMLR, 2021.
  10. Hyperbolic graph convolutional neural networks. Advances in Neural Information Processing Systems, 32:4868–4879, 2019.
  11. Highly scalable and provably accurate classification in poincaré balls. In 2021 IEEE International Conference on Data Mining (ICDM), pages 61–70. IEEE, 2021.
  12. Large-margin classification in hyperbolic space. In The 22nd international conference on artificial intelligence and statistics, pages 1832–1840. PMLR, 2019.
  13. Nested hyperbolic spaces for dimensionality reduction and hyperbolic nn design. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 356–365, 2022.
  14. Geodesic exponential kernels: When curvature and linearity conflict. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3032–3042, 2015.
  15. Hyperbolic entailment cones for learning hierarchical embeddings. In International Conference on Machine Learning, pages 1646–1655. PMLR, 2018.
  16. Hyperbolic neural networks. Advances in Neural Information Processing Systems 31, pages 5345–5355, 2019.
  17. Community structure in social and biological networks. Proceedings of the national academy of sciences, 99(12):7821–7826, 2002.
  18. Sigurdur Helgason. Groups and geometric analysis: integral geometry, invariant differential operators, and spherical functions, volume 83. American Mathematical Society, 2022.
  19. Pymanopt: A python toolbox for optimization on manifolds using automatic differentiation. Journal of Machine Learning Research, 17:1–5, 2016.
  20. Hyperbolic manifold regression. In International Conference on Artificial Intelligence and Statistics, pages 2570–2580. PMLR, 2020.
  21. Emile Mathieu. Charline le lan, chris j maddison, ryota tomioka, and yee whye teh. continuous hierarchical representations with poincaré variational auto-encoders. Advances in Neural Information Processing Systems, pages 12544–12555, 2019.
  22. Gradient-based hierarchical clustering using continuous representations of trees in hyperbolic space. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 714–722, 2019.
  23. Poincaré embeddings for learning hierarchical representations. Advances in neural information processing systems, 30:6338–6347, 2017.
  24. Representation tradeoffs for hyperbolic embeddings. In International conference on machine learning, pages 4460–4469. PMLR, 2018.
  25. Rik Sarkar. Low distortion delaunay embedding of trees in hyperbolic plane. In International Symposium on Graph Drawing, pages 355–366. Springer, 2011.
  26. Hiroyuki Sato. Riemannian conjugate gradient methods: General framework and specific algorithms with convergence analyses. SIAM Journal on Optimization, 32(4):2690–2717, 2022.
  27. Hyperbolic neural networks++. In International Conference on Learning Representations, 2020.
  28. Fully-connected network on noncompact symmetric space and ridgelet transform based on helgason-fourier analysis. In International Conference on Machine Learning, pages 20405–20422. PMLR, 2022.
  29. Poincare glove: Hyperbolic word embeddings. In International Conference on Learning Representations, 2018.
  30. Constantin Udriste. Convex functions and optimization methods on Riemannian manifolds, volume 297. Springer Science & Business Media, 2013.
  31. Pinceton University. About wordnet, 2010.
  32. Ming-Xi Wang. Laplacian eigenspaces, horocycles and neuron models on hyperbolic spaces. 2021.
  33. Robust large-margin learning in hyperbolic space. Advances in Neural Information Processing Systems, 33:17863–17873, 2020.
  34. Hyla: Hyperbolic laplacian features for graph learning. arXiv preprint arXiv:2202.06854, 2022.
  35. Wayne W Zachary. An information flow model for conflict and fission in small groups. Journal of anthropological research, 33(4):452–473, 1977.
  36. First-order methods for geodesically convex optimization. In Conference on Learning Theory, pages 1617–1638. PMLR, 2016.
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now