Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
166 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 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

Semidefinite Relaxations of the Gromov-Wasserstein Distance (2312.14572v3)

Published 22 Dec 2023 in math.OC and stat.ML

Abstract: The Gromov-Wasserstein (GW) distance is an extension of the optimal transport problem that allows one to match objects between incomparable spaces. At its core, the GW distance is specified as the solution of a non-convex quadratic program and is not known to be tractable to solve. In particular, existing solvers for the GW distance are only able to find locally optimal solutions. In this work, we propose a semi-definite programming (SDP) relaxation of the GW distance. The relaxation can be viewed as the Lagrangian dual of the GW distance augmented with constraints that relate to the linear and quadratic terms of transportation plans. In particular, our relaxation provides a tractable (polynomial-time) algorithm to compute globally optimal transportation plans (in some instances) together with an accompanying proof of global optimality. Our numerical experiments suggest that the proposed relaxation is strong in that it frequently computes the globally optimal solution. Our Python implementation is available at https://github.com/tbng/gwsdp.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. E. Abbe. Community detection and stochastic block models: recent developments. The Journal of Machine Learning Research, 18(1):6446–6531, 2017.
  2. M. Agueh and G. Carlier. Barycenters in the Wasserstein space. SIAM Journal on Mathematical Analysis, 43(2):904–924, 2011.
  3. Wasserstein Generative Adversarial Networks. In D. Precup and Y. W. Teh, editors, Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 214–223. PMLR, 06–11 Aug 2017.
  4. M. ApS. The MOSEK optimization toolbox for Python manual. Version 10.0., 2022.
  5. Learning generative models across incomparable spaces. In International conference on machine learning, pages 851–861. PMLR, 2019.
  6. Iterative Bregman projections for regularized transportation problems. SIAM Journal on Scientific Computing, 37(2):A1111–A1138, 2015.
  7. I. M. Bomze and E. de Klerk. Solving standard quadratic optimization problems via linear, semidefinite and copositive programming. J. Global Optim., 24(2):163–185, 2002.
  8. Semidefinite programming based algorithms for sensor network localization. ACM Transactions on Sensor Networks (TOSN), 2(2):188–220, 2006.
  9. Joint distribution optimal transportation for domain adaptation. Advances in neural information processing systems, 30, 2017.
  10. S. Diamond and S. Boyd. CVXPY: A Python-embedded modeling language for convex optimization. Journal of Machine Learning Research, 17(83):1–5, 2016.
  11. POT: Python Optimal Transport. Journal of Machine Learning Research, 22(78):1–8, 2021.
  12. Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming. Journal of the ACM (JACM), 42(6):1115–1145, 1995.
  13. Stochastic blockmodels: First steps. Social networks, 5(2):109–137, 1983.
  14. Sampled Gromov Wasserstein. Machine Learning, 110(8):2151–2186, 2021.
  15. Tight relaxation of quadratic matching. In Computer graphics forum, volume 34, pages 115–128. Wiley Online Library, 2015.
  16. From Word Embeddings To Document Distances. In F. Bach and D. Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 957–966, Lille, France, 07–09 Jul 2015. PMLR.
  17. Flow matching for generative modeling. arXiv preprint arXiv:2210.02747, 2022.
  18. Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003, 2022.
  19. O. Mula and A. Nouy. Moment-SoS Methods for Optimal Transport Problems. arXiv preprint arXiv:2211.10742, 2022.
  20. T. Motzkin and E. G. Straus. Maxima for graphs and a new proof of a theorem of Tur´an. Canadian Journal of Mathematics, 1965.
  21. F. Mémoli. Gromov–Wasserstein Distances and the Metric Approach to Object Matching. Foundations of Computational Mathematics, 11(4):417–487, August 2011.
  22. J. Nocedal and S. J. Wright. Numerical Optimization. Springer, 2006.
  23. Conic Optimization via Operator Splitting and Homogeneous Self-Dual Embedding. Journal of Optimization Theory and Applications, 169(3):1042–1068, June 2016.
  24. Computational optimal transport: With applications to data science. Foundations and Trends® in Machine Learning, 11(5-6):355–607, 2019.
  25. Gromov-wasserstein averaging of kernel and distance matrices. In International conference on machine learning, pages 2664–2672. PMLR, 2016.
  26. Quadratic programming with one negative eigenvalue is NP-hard. Journal of Global optimization, 1(1):15–22, 1991.
  27. Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces. arXiv preprint arXiv:2307.09057, 2023.
  28. Linear-time gromov wasserstein distances using low rank couplings and costs. In International Conference on Machine Learning, pages 19347–19365. PMLR, 2022.
  29. The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation. In Advances in Neural Information Processing Systems, volume 34, pages 8766–8779, 2021.
  30. Template based Graph Neural Network with Optimal Transport Distances. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems, volume 35, pages 11800–11814. Curran Associates, Inc., 2022.
  31. Optimal Transport for structured data with application on graphs. In K. Chaudhuri and R. Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 6275–6284. PMLR, 09–15 Jun 2019.
  32. Online Graph Dictionary Learning. In M. Meila and T. Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 10564–10574. PMLR, 18–24 Jul 2021.
  33. Sliced Gromov-Wasserstein. In Advances in Neural Information Processing Systems, volume 33, pages 14753–14763, 2019.
  34. Gromov-Wasserstein Learning for Graph Matching and Node Embedding. In K. Chaudhuri and R. Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 6932–6941. PMLR, 09–15 Jun 2019.
Citations (1)
View on Semantic Scholar

Summary

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

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

Tweets