Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational Wasserstein Barycenters with C-cyclical Monotonicity Regularization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add c-cyclical monotonicity regularization (ablation) | VWB · Multivariate Gaussians, D=256 | BW2²-UVP: 14.65 -> 1.10 | Helped |
| add c-cyclical monotonicity regularization (ablation) | VWB · Multivariate Gaussians, D=128 | BW2²-UVP: 5.01 -> 0.40 | Helped |
| represent the barycenter with a variational distribution instead of a fixed prior | CRWB · Multivariate Gaussians, D=256 | BW2²-UVP: >100 -> 14.65 | Helped |
| use VWB-CMR rather than the strongest listed baseline | Multivariate Gaussians, D=256 · Multivariate Gaussians, D=256 | BW2²-UVP: 3.41 -> 1.10 | Helped |
| use VWB-CMR rather than the strongest listed baseline | Bike Sharing subset posterior aggregation · Bike Sharing subset posterior aggregation | BW2²-UVP: 0.13 -> 0.10 | Helped |
| use quadratic rather than entropy regularization (ablation) | VWB-CMR · Multivariate Gaussians, D=128 and D=256 | convergence stability | Helped |
| increase the number of permutations in the c-cyclical monotonicity regularization beyond one or two (ablation) | VWB-CMR · Wasserstein barycenter experiments | barycenter performance | Hurt |
| use two permutations rather than one in the c-cyclical monotonicity regularization (ablation) | VWB-CMR · Wasserstein barycenter experiments | barycenter performance | Mixed |
| use VWB-CMR rather than CRWB | Bike Sharing subset posterior aggregation · Bike Sharing subset posterior aggregation | BW2²-UVP: 0.96 -> 0.10 | Helped |
Closest papers by meaning
- Continuous Regularized Wasserstein Barycenters (NeurIPS 2020 · similarity 0.94)
- Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization (ICML 2025 · similarity 0.91)
- Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows (ICML 2025 · similarity 0.89)
- A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures (NeurIPS 2026 · similarity 0.89)
- Estimating Barycenters of Distributions with Neural Optimal Transport (ICML 2024 · similarity 0.89)
- Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness (ICML 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.