Research map / Learning theory and algorithms / Optimal transport
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
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 |
|---|---|---|---|
| Use PReLU activation instead of ReLU or leaky ReLU in the barycenter neural networks | ICNN-based Wasserstein barycenter algorithm (NWB/CWB) · high-dimensional and 2D/3D barycenter experiments | barycenter approximation performance | Helped |
| Vary number of hidden layers (3 to 4) in the barycenter networks | ICNN-based Wasserstein barycenter algorithm · high-dimensional barycenter experiments | barycenter approximation performance | No clear effect |
| Adding a constraint that pushforward measures grad g_i # mu_i are equal across marginals | ICNN-based Wasserstein barycenter algorithm · barycenter problem | barycenter quality | No clear effect |
| Train the proposed method with inner optimization cycles instead of CRWB/CWB baselines | proposed ICNN barycenter method · training time comparison | training time: almost once to twice longer | Hurt |
Closest papers by meaning
- Estimating Barycenters of Distributions with Neural Optimal Transport (ICML 2024 · similarity 0.91)
- Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization (ICML 2025 · similarity 0.88)
- Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness (ICML 2025 · similarity 0.88)
- A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures (NeurIPS 2026 · similarity 0.88)
- On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity (ICML 2024 · similarity 0.86)
- Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows (ICML 2025 · 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.