Research map / Learning theory and algorithms / Optimal transport
Wasserstein losses for generative models
Train generative models with Wasserstein and sliced losses, with asymptotic and convergence guarantees.
23 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Optimal transport, keyword cluster “wasserstein distance · sliced · sw”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
1 papers in 2023–24 and 1 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 1.2% to 0.7%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2018 · Sliced Wasserstein Distance for Learning Gaussian Mixture Models (CVPR 2018 · 111 citations)
- 2019 · Max-Sliced Wasserstein Distance and Its Use for GANs (CVPR 2019 · 148 citations)
- 2020 · A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions (NeurIPS 2020 · 33 citations)
- 2021 · A Sliced Wasserstein Loss for Neural Texture Synthesis (CVPR 2021 · 65 citations)
- 2022 · Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance (NeurIPS 2022 · 4 citations)
- 2023 · Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals (ICML 2023 · 1 citation)
- 2026 · MIND: Monge Inception Distance for Generative Models Evaluation (NeurIPS 2026 · 0 citations)
Earliest papers here
- Sliced Wasserstein Distance for Learning Gaussian Mixture Models (CVPR 2018 · 111 citations)
- Minimax Statistical Learning with Wasserstein distances (NeurIPS 2018 · 72 citations)
- On the Convergence and Robustness of Training GANs with Regularized Optimal Transport (NeurIPS 2018 · 58 citations)
What has been tried
22 papers here report 172 measured changes (a component added, removed or swapped, compared with a baseline): helped 66%, no clear effect 8%, hurt 22%, mixed 5%. Papers mostly publish changes that helped, so "helped" is over-represented.
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 21 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Wasserstein barycenters and GW (55 papers)
- Sliced Wasserstein variants (50 papers)
Elsewhere in the topic
- Neural optimal transport (99 papers)
- Transport map estimation (77 papers)
- Sinkhorn and entropic OT algorithms (69 papers)
- Schrodinger bridge matching (11 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).