Research map / Optimization / Optimizers
Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels
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 |
|---|---|---|---|
| Neural forward scheme instead of neural backward scheme | interaction energy flow with Riesz kernel r=1 · d=2 benchmark against analytic flow | discrepancy D2K to analytic flow | Helped |
| Neural backward scheme instead of particle flow | interaction energy flow with Riesz kernel r=1.5 · d=2 benchmark against analytic flow | discrepancy D2K to analytic flow | Helped |
| Neural backward scheme vs particle flow for Riesz r=0.5 | interaction energy flow with Riesz kernel r=0.5 · d=2 benchmark against analytic flow | discrepancy D2K to analytic flow | No clear effect |
| Particle flow instead of neural schemes in high dimension | interaction energy flow with r=1, d=1000 and d=10 · benchmark against analytic flow | discrepancy D2K to analytic flow | Helped |
| Particle flow instead of neural schemes in 3D | interaction energy flow with r=1, d=3 · benchmark against analytic flow | discrepancy D2K to analytic flow | Hurt |
| Neural forward scheme requires r=1 (not defined for other r) | neural forward scheme · interaction energy flow benchmark | well-definedness | Hurt |
Closest papers by meaning
- Flowing Datasets with Wasserstein over Wasserstein Gradient Flows (ICML 2025 · similarity 0.86)
- Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points (NeurIPS 2025 · similarity 0.86)
- Generative Sliced MMD Flows with Riesz Kernels (ICLR 2024 · similarity 0.86)
- Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once (NeurIPS 2026 · similarity 0.86)
- Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space (NeurIPS 2025 · similarity 0.86)
- SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures (NeurIPS 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.