Research map / Learning theory and algorithms / Optimal transport
HOTA: Hamiltonian framework for Optimal Transport Advection
Nazar Buzun, Daniil Shlenskii, Maksim Bobrin, Dmitry V. Dylov
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 |
|---|---|---|---|
| add replay buffer of simulation history (ablation) | HOTA · Vneck | feasibility W2: 16.47 -> 0.002 | Improved |
| add replay buffer of simulation history (ablation) | HOTA · GMM | feasibility W2: 1.248 -> 0.19 | Improved |
| add replay buffer of simulation history (ablation) | HOTA · Stunnel | optimality (integral cost): 706.89 -> 320.90 | Improved |
| add replay buffer of simulation history (ablation) | HOTA · Vneck | optimality (integral cost): 82.49 -> 115.09 | Hurt |
| add adaptive gradient balancing (ablation) | HOTA · Stunnel | feasibility W2: 3.60 -> 0.006 | Improved |
| add adaptive gradient balancing (ablation) | HOTA · GMM | feasibility W2: 2.64 -> 0.19 | Improved |
| add adaptive gradient balancing (ablation) | HOTA · GMM | optimality (integral cost): 72.77 -> 80.44 | Hurt |
| add adaptive gradient balancing (ablation) | HOTA · Vneck | optimality (integral cost): 109.25 -> 115.09 | Hurt |
| increase acceleration coefficient lambda_a (ablation) | HOTA · Stunnel, GMM | optimality vs feasibility | Mixed |
| increase control weight lambda_hjb (ablation) | HOTA · Stunnel, GMM | optimality vs feasibility | Mixed |
| replace GSBM with HOTA | GSBM · GMM | feasibility W2: 4.13 -> 0.19 | Improved |
Closest papers by meaning
- A Computational Framework for Solving Wasserstein Lagrangian Flows (ICML 2024 · similarity 0.87)
- Progressive Entropic Optimal Transport Solvers (NeurIPS 2024 · similarity 0.87)
- Dynamic Conditional Optimal Transport through Simulation-Free Flows (NeurIPS 2024 · similarity 0.86)
- Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows (ICML 2025 · similarity 0.85)
- On the Relation between Rectified Flows and Optimal Transport (NeurIPS 2025 · similarity 0.85)
- Flow Matching from Viewpoint of Proximal Operators (NeurIPS 2026 · similarity 0.85)
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.
