mlsanityData to 7 Oct 2026

Meta Optimal Transport

arXiv 2206.05262 ↗First posted 10 Jun 2022cs.LG cs.AI stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

We study the use of amortized optimization to predict optimal transport (OT) maps from the input measures, which we call Meta OT. This helps repeatedly solve similar OT problems between different measures by leveraging the knowledge and information present from past problems to rapidly predict and solve new problems. Otherwise, standard methods ignore the knowledge of the past solutions and suboptimally re-solve each problem from scratch. We instantiate Meta OT models in discrete and continuous settings between grayscale images, spherical data, classification labels, and color palettes and use them to improve the computational time of standard OT solvers. Our source code is available at http://github.com/facebookresearch/meta-ot

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 55 of its 106 references that are in the map. First posted on arXiv 10 Jun 2022.

Builds on

55 of 106 references.

References · 55

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  5. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 722
  6. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2018Conditional Neural Processescited by 421
  9. 2021Neural Operator: Learning Maps Between Function Spacescited by 413
  10. 2016Input Convex Neural Networkscited by 407
  11. 2017Learning Generative Models with Sinkhorn Divergencescited by 310
  12. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
38 more
  1. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  2. 2017Near-linear time approximation algorithms for optimal transport via Sinkhorn iterationcited by 219
  3. 2021Learning to Optimize: A Primer and A Benchmarkcited by 206
  4. 2019Generalized Sliced Wasserstein Distancescited by 205
  5. 2019Optimal transport mapping via input convex neural networkscited by 202
  6. 2015Learning with a Wasserstein Losscited by 194
  7. 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 167
  8. 2019Wasserstein Fair Classificationcited by 131
  9. 2022Neural Optimal Transportcited by 123
  10. 2017Large-Scale Optimal Transport and Mapping Estimationcited by 120
  11. 2020Primal Wasserstein Imitation Learningcited by 120
  12. 2019Max-Sliced Wasserstein Distance and its use for GANscited by 118
  13. 2019Wasserstein-2 Generative Networkscited by 96
  14. 2022Optimal Transport Tools (OTT): A JAX Toolbox for all things Wassersteincited by 96
  15. 2021Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmarkcited by 95
  16. 2021Proximal Optimal Transport Modeling of Population Dynamicscited by 91
  17. 2020Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimizationcited by 89
  18. 2021Generative Modeling with Optimal Transport Mapscited by 80
  19. 2021Large-Scale Wasserstein Gradient Flowscited by 76
  20. 2018Optimal Transport for Multi-source Domain Adaptation under Target Shiftcited by 67
  21. 2021Low-Rank Sinkhorn Factorizationcited by 66
  22. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 64
  23. 2021Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costscited by 61
  24. 2021Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimizationcited by 50
  25. 2021Cross-Domain Imitation Learning via Optimal Transportcited by 49
  26. 2018Statistical Optimal Transport via Factored Couplingscited by 38
  27. 20192-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANscited by 32
  28. 2020Continuous Regularized Wasserstein Barycenterscited by 32
  29. 2018Optimal Transport: Fast Probabilistic Approximation with Exact Solverscited by 27
  30. 2020Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Trainingcited by 27
  31. 2017Learning Wasserstein Embeddingscited by 25
  32. 2019Subspace Detours: Building Transport Plans that are Optimal on Subspace Projectionscited by 19
  33. 2019Screening Sinkhorn Algorithm for Regularized Optimal Transportcited by 17
  34. 2022Amortized Projection Optimization for Sliced Wasserstein Generative Modelscited by 17
  35. 2017Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transportcited by 16
  36. 2019Wasserstein Adversarial Regularization (WAR) on label noisecited by 16
  37. 2021Riemannian Convex Potential Mapscited by 16
  38. 2019Conservative Wasserstein Training for Pose Estimationcited by 11

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 7; 2025: 4; 2026: 8.

28 papers.

Sort:

By area:

  1. 2024Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifoldcited by 41
  2. 2022Sparsity-Constrained Optimal Transportcited by 32
  3. 2022On amortizing convex conjugates for optimal transportcited by 30
  4. 2023Scalable Optimal Transport Methods in Machine Learning: A Contemporary Surveycited by 27
  5. 2024Wasserstein Flow Matching: Generative modeling over families of distributionscited by 27
  6. 2023Quasi-Monte Carlo for 3D Sliced Wassersteincited by 22
  7. 2022Rethinking Initialization of the Sinkhorn Algorithmcited by 14
  8. 2024Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformerscited by 14
  9. 2022Universal Neural Optimal Transportcited by 6
  10. 2025DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flowscited by 4
  11. 2022GeONet: a neural operator for learning the Wasserstein geodesiccited by 3
  12. 2024Unsupervised Solution Operator Learning for Mean-Field Games via Sampling-Invariant Parametrizationscited by 3
16 more
  1. 2024Zero-Shot Offline Imitation Learning via Optimal Transportcited by 3
  2. 2025Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphscited by 3
  3. 2026MapPFN: Learning Causal Perturbation Maps in Contextcited by 3
  4. 2023DeepEMD: A Transformer-based Fast Estimation of the Earth Mover's Distancecited by 2
  5. 2026Amortized Optimal Transport from Sliced Potentialscited by 2
  6. 2026Measure-to-measure Regression with Transformerscited by 1
  7. 2026SCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Modelscited by 1
  8. 2023Learning to Re-rank with Constrained Meta-Optimal Transportcited by 0
  9. 2024On the impact of measure pre-conditionings on general parametric ML models and transfer learning via domain adaptationcited by 0
  10. 2024CLAMS: A System for Zero-Shot Model Selection for Clusteringcited by 0
  11. 2025Embedding Empirical Distributions for Computing Optimal Transport Mapscited by 0
  12. 2025Automated Machine Learning for Unsupervised Tabular Taskscited by 0
  13. 2026Reliable Modeling of Distribution Shifts via Displacement-Reshaped Optimal Transportcited by 0
  14. 2026ASAP: Amortized Doubly-Stochastic Attention via Sliced Dual Projectioncited by 0
  15. 2026FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policycited by 0
  16. 2026DrainSinkhorn: Safe Elimination for Batched Entropic Optimal Transportcited by 0