AI Paper Atlas

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

NeurIPS 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use KALE flow instead of MMD flow for a target on three ringsKALE flow · three rings hypersurface targetrecovery of target supportImproved
Use KALE flow instead of MMD flow and Sinkhorn descent for heart-to-spiral transferKALE flow · heart to spiral disjoint supportsspeed of recovering spiral shapeMixed
Vary regularization lambda from small to large (ablation)KALE flow · 4-Gaussian mixtureWasserstein distance to ULA or MMD particlesMixed
Add noise injection with tuned beta_n schedule (ablation)KALE flow · three examplesproximity to global minimumImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy