Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Learning Ultrametric Trees for Optimal Transport Regression (2210.12288v2)

Published 21 Oct 2022 in cs.LG

Abstract: Optimal transport provides a metric which quantifies the dissimilarity between probability measures. For measures supported in discrete metric spaces, finding the optimal transport distance has cubic time complexity in the size of the space. However, measures supported on trees admit a closed-form optimal transport that can be computed in linear time. In this paper, we aim to find an optimal tree structure for a given discrete metric space so that the tree-Wasserstein distance approximates the optimal transport distance in the original space. One of our key ideas is to cast the problem in ultrametric spaces. This helps us optimize over the space of ultrametric trees -- a mixed-discrete and continuous optimization problem -- via projected gradient decent over the space of ultrametric matrices. During optimization, we project the parameters to the ultrametric space via a hierarchical minimum spanning tree algorithm, equivalent to the closest projection to ultrametrics under the supremum norm. Experimental results on real datasets show that our approach outperforms previous approaches (e.g. Flowtree, Quadtree) in approximating optimal transport distances. Finally, experiments on synthetic data generated on ground truth trees show that our algorithm can accurately uncover the underlying trees.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. On the approximability of numerical taxonomy (fitting distances by tree metrics). SIAM Journal on Computing, 28(3):1073–1085, 1998.
  2. Wasserstein generative adversarial networks. In International conference on machine learning, pages 214–223. PMLR, 2017.
  3. Scalable nearest neighbor search for optimal transport. arXiv preprint arXiv:1910.04126, 2019.
  4. l∞subscript𝑙l_{\infty}italic_l start_POSTSUBSCRIPT ∞ end_POSTSUBSCRIPT-approximation via subdominants. Journal of mathematical psychology, 44(4):600–616, 2000.
  5. Marco Cuturi. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, 26, 2013.
  6. Texture mapping via optimal mass transport. IEEE transactions on visualization and computer graphics, 16(3):419–433, 2009.
  7. Bayesian inference with optimal maps. Journal of Computational Physics, 231(23):7815–7850, 2012.
  8. The phylogenetic kantorovich–rubinstein metric for environmental sequence samples. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 74(3):569–592, 2012.
  9. A tight bound on approximating arbitrary metrics by tree metrics. In Proceedings of the thirty-fifth annual ACM symposium on Theory of computing, pages 448–455, 2003.
  10. Pot: Python optimal transport. Journal of Machine Learning Research, 22(78):1–8, 2021. URL http://jmlr.org/papers/v22/20-451.html.
  11. Learning with a wasserstein loss. Advances in neural information processing systems, 28, 2015.
  12. Stochastic optimization for large-scale optimal transport. Advances in neural information processing systems, 29, 2016.
  13. Supervised word mover’s distance. Advances in neural information processing systems, 29, 2016.
  14. Fast image retrieval via embeddings. In 3rd international workshop on statistical and computational theories of vision, volume 2, page 5. Nice, France, 2003.
  15. Optimal mass transport: Signal processing and machine-learning applications. IEEE signal processing magazine, 34(4):43–59, 2017.
  16. A collection of public transport network data sets for 25 cities. Scientific data, 5(1):1–14, 2018.
  17. Dynamical optimal transport on discrete surfaces. ACM Transactions on Graphics (TOG), 37(6):1–16, 2018.
  18. Tree-wasserstein barycenter for large-scale multilevel clustering and scalable bayes. arXiv preprint arXiv:1910.04483, 2019a.
  19. Tree-sliced variants of wasserstein distances. Advances in neural information processing systems, 32, 2019b.
  20. Minimax statistical learning with wasserstein distances. Advances in Neural Information Processing Systems, 31, 2018.
  21. Wasserstein training of restricted boltzmann machines. Advances in Neural Information Processing Systems, 29, 2016.
  22. Amplitude and phase variation of point processes. The Annals of Statistics, 44(2):771–812, 2016.
  23. Fast and robust earth mover’s distances. In 2009 IEEE 12th international conference on computer vision, pages 460–467. IEEE, 2009.
  24. Wasserstein barycenter and its application to texture mixing. In International Conference on Scale Space and Variational Methods in Computer Vision, pages 435–446. Springer, 2011.
  25. Sebastian Reich. A nonparametric ensemble transform method for bayesian inference. SIAM Journal on Scientific Computing, 35(4):A2013–A2024, 2013.
  26. The network data repository with interactive graph analytics and visualization. In AAAI, 2015. URL https://networkrepository.com.
  27. The earth mover’s distance as a metric for image retrieval. International journal of computer vision, 40(2):99–121, 2000.
  28. Wasserstein propagation for semi-supervised learning. In International Conference on Machine Learning, pages 306–314. PMLR, 2014.
  29. Convolutional wasserstein distances: Efficient optimal transportation on geometric domains. ACM Transactions on Graphics (ToG), 34(4):1–11, 2015.
  30. Fixed support tree-sliced wasserstein barycenter. arXiv preprint arXiv:2109.03431, 2021.
  31. Cédric Villani. Optimal transport: old and new, volume 338. Springer, 2009.
  32. Approximating 1-wasserstein distance with trees. arXiv preprint arXiv:2206.12116, 2022.
  33. A taxonomy of transcriptomic cell types across the isocortex and hippocampal formation. Cell, 184(12):3222–3241, 2021.
Citations (2)
View on Semantic Scholar

Summary

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

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