AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Moser Flow: Divergence-based Generative Modeling on Manifolds

Noam Rozen, Aditya Grover, Maximilian Nickel, Yaron Lipman

NeurIPS 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 5 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 Moser Flow instead of Riemannian CNFMoser Flow · VolcanoNLL: -0.97_{\pm 0.15} -> \mathbf{-2.02}_{\pm 0.42}Improved
Use Moser Flow instead of Riemannian CNFMoser Flow · EarthquakeNLL: 0.19_{\pm 0.04} -> \mathbf{-0.09}_{\pm 0.02}Improved
Use Moser Flow instead of Riemannian CNFMoser Flow · FloodNLL: 0.90_{\pm 0.03} -> \mathbf{0.62}_{\pm 0.04}Improved
Use Moser Flow instead of Riemannian CNFMoser Flow · FireNLL: -0.66_{\pm 0.05} -> \mathbf{ -1.03}_{\pm 0.03}Improved
Increase the penalty weight λMoser Flow · Toy distributionsAgreement between learned density and push-forward densityImproved
Use Moser Flow instead of FFJORDMoser Flow · Flat Torus high-frequency image densityTraining iteration time: 1-2 order of magnitudes fasterImproved
Use Moser Flow instead of FFJORDMoser Flow · Flat Torus high-frequency image densityNLLImproved

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