mlsanityData to 14 Oct 2026

Recent Advances in Optimal Transport for Machine Learning

arXiv 2306.16156 ↗First posted 28 Jun 2023cs.LG math.PR stat.MLcited by 66

Not on the map. Why?

Abstract (arXiv)

Recently, Optimal Transport has been proposed as a probabilistic framework in Machine Learning for comparing and manipulating probability distributions. This is rooted in its rich history and theory, and has offered new solutions to different problems in machine learning, such as generative modeling and transfer learning. In this survey we explore contributions of Optimal Transport for Machine Learning over the period 2012 -- 2023, focusing on four sub-fields of Machine Learning: supervised, unsupervised, transfer and reinforcement learning. We further highlight the recent development in computational Optimal Transport and its extensions, such as partial, unbalanced, Gromov and Neural Optimal Transport, and its interplay with Machine Learning practice.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). Builds on 86 of its 202 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

86 of 202 references.

References · 86

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  7. 2017Improved Training of Wasserstein GANscited by 2,235
  8. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  9. 2016Variational Inference: A Review for Statisticianscited by 1,472
  10. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  11. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 669
  12. 2018Deep Visual Domain Adaptation: A Surveycited by 635
38 more
  1. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  2. 2015Optimal Transport for Domain Adaptationcited by 463
  3. 2016Input Convex Neural Networkscited by 414
  4. 2017Wasserstein Auto-Encoderscited by 373
  5. 2020Fairness in Machine Learning: A Surveycited by 370
  6. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  7. 2015Adversarial Autoencoderscited by 364
  8. 2017Learning Generative Models with Sinkhorn Divergencescited by 314
  9. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 282
  10. 2020How to train your neural ODE: the world of Jacobian and kinetic regularizationcited by 228
  11. 2013Fast Computation of Wasserstein Barycenterscited by 216
  12. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 214
  13. 2019Generalized Sliced Wasserstein Distancescited by 208
  14. 2019Optimal transport mapping via input convex neural networkscited by 206
  15. 2015Learning with a Wasserstein Losscited by 196
  16. 2018Optimal Transport for structured data with application on graphscited by 172
  17. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 170
  18. 2020Geometric Dataset Distances via Optimal Transportcited by 158
  19. 2020OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transportcited by 143
  20. 2015Optimal Entropy-Transport problems and a new Hellinger-Kantorovich distance between positive measurescited by 139
  21. 2022Neural Optimal Transportcited by 126
  22. 2021Unbalanced minibatch Optimal Transport; applications to Domain Adaptationcited by 125
  23. 2017Large-Scale Optimal Transport and Mapping Estimationcited by 123
  24. 2017The Cramer Distance as a Solution to Biased Wasserstein Gradientscited by 119
  25. 2019Max-Sliced Wasserstein Distance and its use for GANscited by 119
  26. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  27. 2022Optimal Transport Tools (OTT): A JAX Toolbox for all things Wassersteincited by 101
  28. 2019Wasserstein-2 Generative Networkscited by 97
  29. 2021Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmarkcited by 96
  30. 2019Subspace Robust Wasserstein Distancescited by 90
  31. 2019Learning with minibatch Wasserstein : asymptotic and gradient propertiescited by 87
  32. 2020Statistical and Topological Properties of Sliced Probability Divergencescited by 85
  33. 2017Regularization via Mass Transportationcited by 81
  34. 2018Optimal Transport for Multi-source Domain Adaptation under Target Shiftcited by 68
  35. 2021OTCE: A Transferability Metric for Cross-Domain Cross-Task Representationscited by 62
  36. 2019Sliced Wasserstein Generative Modelscited by 61
  37. 2017Sliced Wasserstein Distance for Learning Gaussian Mixture Modelscited by 59
  38. 2018Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distancecited by 56

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 13; 2025: 34; 2026: 15.

66 papers.

Sort:

By area:

  1. 2025TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Modelcited by 57
  2. 2025The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutionscited by 26
  3. 2024Beyond FVD: Enhanced Evaluation Metrics for Video Generation Qualitycited by 22
  4. 2024LanDA: Language-Guided Multi-Source Domain Adaptationcited by 13
  5. 2023Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Spacecited by 12
  6. 2025Differentiable Generalized Sliced Wasserstein Planscited by 7
  7. 2024The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learningcited by 6
  8. 2024ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transportcited by 6
  9. 2025Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transportcited by 6
  10. 2025Your contrastive learning problem is secretly a distribution alignment problemcited by 6
  11. 2024Lighter, Better, Faster Multi-Source Domain Adaptation with Gaussian Mixture Models and Optimal Transportcited by 5
  12. 2025PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transportcited by 5
38 more
  1. 2023Benchmarking Domain Adaptation for Chemical Processes on the Tennessee Eastman Processcited by 4
  2. 2023Federated Dataset Dictionary Learning for Multi-Source Domain Adaptationcited by 4
  3. 2023Group-blind optimal transport to group parity and its constrained variantscited by 4
  4. 2024Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Modelcited by 4
  5. 2025Unsupervised Anomaly Detection through Mass Repulsing Optimal Transportcited by 4
  6. 2025Towards Reasoning-Preserving Unlearning in Multimodal Large Language Modelscited by 4
  7. 2024Optimal Transport for Domain Adaptation through Gaussian Mixture Modelscited by 3
  8. 2025A dimensionality reduction technique based on the Gromov-Wasserstein distancecited by 3
  9. 2025Schr"odinger bridge for generative AI: Soft-constrained formulation and convergence analysiscited by 3
  10. 2026DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Modelscited by 3
  11. 2025Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomenacited by 2
  12. 2025Wasserstein Barycenter Gaussian Process based Bayesian Optimizationcited by 2
  13. 2025Constrained Sliced Wasserstein Embeddingcited by 2
  14. 2026Structure-Preserving Multi-View Embedding Using Gromov-Wasserstein Optimal Transportcited by 2
  15. 2024GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attentioncited by 1
  16. 2024Dataset Dictionary Learning in a Wasserstein Space for Federated Domain Adaptationcited by 1
  17. 2024Learning signals defined on graphs with optimal transport and Gaussian process regressioncited by 1
  18. 2025Double-Bounded Nonlinear Optimal Transport for Size Constrained Min Cut Clusterincited by 1
  19. 2025Scalable Learning from Probability Measures with Mean Measure Quantizationcited by 1
  20. 2025Decentralized Federated Dataset Dictionary Learning for Multi-Source Domain Adaptationcited by 1
  21. 2025VeLU: Variance-enhanced Learning Unit for Deep Neural Networkscited by 1
  22. 2025HOTA: Hamiltonian framework for Optimal Transport Advectioncited by 1
  23. 2025Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspectivecited by 1
  24. 2025Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computationcited by 1
  25. 2025Multivariate Uncertainty Quantification with Tomographic Quantile Forestscited by 1
  26. 2026Static and Dynamic Approaches to Computing Barycenters of Probability Measures on Graphscited by 1
  27. 2026Gromov-Wasserstein Methods for Multi-View Relational Embedding and Clusteringcited by 1
  28. 2024Decentralized and Equitable Optimal Transportcited by 0
  29. 2024Online Multi-Source Domain Adaptation through Gaussian Mixtures and Dataset Dictionary Learningcited by 0
  30. 2024Fused Gromov-Wasserstein Variance Decomposition with Linear Optimal Transportcited by 0
  31. 2025Constrained Gaussian Wasserstein Optimal Transport with Commutative Covariance Matricescited by 0
  32. 2025KD2M: A unifying framework for feature knowledge distillationcited by 0
  33. 2025Scalable Approximate Algorithms for Optimal Transport Linear Modelscited by 0
  34. 2025Quantization-based Bounds on the Wasserstein Metriccited by 0
  35. 2025Feature Shift Localization Networkcited by 0
  36. 2025From Coarse to Nuanced: Cross-Modal Alignment of Fine-Grained Linguistic Cues and Visual Salient Regions for Dynamic Emotion Recognitioncited by 0
  37. 2025Gromov-Wasserstein and optimal transport: from assignment problems to probabilistic numericcited by 0
  38. 2025New Algorithmic Directions in Optimal Transport and Applications for Product Spacescited by 0

50 most cited of 66 All 66 (JSON)