AI Paper Atlas

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

Density estimation on low-dimensional manifolds: an inflation-deflation approach

Christian Horvat, Jean-Pascal Pfister

JMLR 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Normalizing flow training and design · 12 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 inflation-deflation instead of M-flow for density evaluationMNIST digit 1 density model · MNIST digit 1 (1000 digits)evaluation time: 17.5 hours -> less than 10 secondsImproved
use IID instead of M-flow for OOD detectionMNIST digit 1 likelihood · MNIST OODarea of intersection: 0.07 for both methodsNo clear effect
add normal-space noise (NID) in place of full Gaussian noise (IID) (ablation)inflation-deflation · circle and surfaces, KS statisticrange of usable sigma^2Improved
use NID/IID trained in data space instead of FOM trained in latent spacedensity estimation on manifolds · surfaces, KS statisticKS statisticNo clear effect
use IID instead of NID (ablation)inflation-deflation · manifold with peaked latent density (Figure C)optimal KSImproved
increase embedding dimension D from 2 to 20 for the circle (ablation)NID and IID · circle in R^D, KS statisticoptimal KSNo clear effect

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