Research map / Optimization / Implicit bias and generalization
Maximum Mean Discrepancy Gradient Flow
Michael Arbel, Anna Korba, Adil SALIM, Arthur Gretton
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 |
|---|---|---|---|
| inject Gaussian noise into the gradient evaluation point of MMD flow | MMD flow (student-teacher network) · Teacher-student regression | training error | Improved |
| use noise injection instead of adding a diffusion term (ablation) | MMD flow · Teacher-student regression | validation error | Improved |
| vary noise level of injection vs diffusion (ablation) | noisy MMD flow · Teacher-student regression | error vs noise level | Improved |
| replace KSD flow with noisy MMD flow (ablation) | MMD flow · Teacher-student regression | computational cost | Improved |
Closest papers by meaning
- Sobolev Regularized MMD Gradient Flow (NeurIPS 2026 · similarity 0.91)
- Generative Sliced MMD Flows with Riesz Kernels (ICLR 2024 · similarity 0.89)
- Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel (ICLR 2024 · similarity 0.88)
- Deep MMD Gradient Flow without adversarial training (ICLR 2025 · similarity 0.87)
- Flow matching achieves almost minimax optimal convergence (ICLR 2025 · similarity 0.86)
- Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent (ICLR 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.
