Research map / Probabilistic and scientific modeling / Variational and generative sampling
Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching
Jannis Chemseddine, Paul Hagemann, Gabriele Steidl, Christian Wald
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use OT coupling (beta=20) instead of random coupling in Bayesian flow matching | Bayesian flow matching · GMM posterior (10 Euler steps) | Sinkhorn distance: 0.0247 -> 0.0225 | Improved |
| use OT coupling (beta=20) with fewer sampling steps | Bayesian flow matching · GMM posterior (3 Euler steps) | Sinkhorn distance: 0.1044 -> 0.0760 | Improved |
| increase beta in the relaxed conditional distance (ablation) | particle flow on MNIST · Class conditional MNIST | label fit | Improved |
| increase beta (ablation) | OT Bayesian flow matching · CIFAR10 class-conditional | FID / class fidelity | Improved |
| use OT couplings instead of diagonal plans (ablation) | class-conditional flow matching · CIFAR10 class-conditional | image quality (FID) | Improved |
Closest papers by meaning
- Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel (ICLR 2024 · similarity 0.89)
- CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching (NeurIPS 2025 · similarity 0.87)
- Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once (NeurIPS 2026 · similarity 0.87)
- A Theory on Flow Matching with Neural Networks (NeurIPS 2026 · similarity 0.87)
- Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching (NeurIPS 2024 · similarity 0.87)
- Dynamic Conditional Optimal Transport through Simulation-Free Flows (NeurIPS 2024 · similarity 0.86)
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.
