Research map / Probabilistic and scientific modeling / Variational and generative sampling
KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support
Pierre Glaser, Michael Arbel, 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 |
|---|---|---|---|
| Use KALE flow instead of MMD flow for a target on three rings | KALE flow · three rings hypersurface target | recovery of target support | Improved |
| Use KALE flow instead of MMD flow and Sinkhorn descent for heart-to-spiral transfer | KALE flow · heart to spiral disjoint supports | speed of recovering spiral shape | Mixed |
| Vary regularization lambda from small to large (ablation) | KALE flow · 4-Gaussian mixture | Wasserstein distance to ULA or MMD particles | Mixed |
| Add noise injection with tuned beta_n schedule (ablation) | KALE flow · three examples | proximity to global minimum | Improved |
Closest papers by meaning
- Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence (NeurIPS 2024 · similarity 0.87)
- Theoretical guarantees in KL for Diffusion Flow Matching (NeurIPS 2024 · similarity 0.86)
- Functional Gradient Flows for Constrained Sampling (NeurIPS 2024 · similarity 0.84)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.84)
- Decoupled Kullback-Leibler Divergence Loss (NeurIPS 2024 · similarity 0.84)
- Sobolev Regularized MMD Gradient Flow (NeurIPS 2026 · similarity 0.84)
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.
