AI Paper Atlas

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

Flowification: Everything is a normalizing flow

Bálint Máté, Samuel Klein, Tobias Golling, François Fleuret

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Normalizing flow training and design · 1 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
sample augmentation noise from normal instead of uniform (ablation)fConv1 · CIFAR-10BPD: 6.24 -> 4.91Improved
sample augmentation noise from normal instead of uniform (ablation)fConv1 · MNISTBPD: 3.41 -> 3.11Improved
use non-overlapping kernels (fConv2) instead of overlapping (fConv1)flowified convolutional network · MNISTBPD: 3.11 -> 1.41Improved
use non-overlapping kernels (fConv2) instead of overlapping (fConv1)flowified convolutional network · CIFAR-10BPD: 4.91 -> 4.20Improved
use convolutional layers instead of linear-only layersflowified network · MNISTBPD: 4.19 -> 3.11Improved
use convolutional layers instead of linear-only layersflowified network · CIFAR-10BPD: 5.45 -> 4.91Improved
add rational quadratic spline (NSF) layers between flowified layersfConv1 · MNISTBPD: 3.11 -> 2.70Improved
add rational quadratic spline (NSF) layers between flowified layersfConv1 · CIFAR-10BPD: 4.91 -> 3.93Improved
add rational quadratic spline (NSF) layers between flowified layersfConv2 · MNISTBPD: 1.41 -> 1.35Improved
add rational quadratic spline (NSF) layers between flowified layersfConv2 · CIFAR-10BPD: 4.20 -> 3.69Improved
use flowified MLP instead of Neural Spline Flowtabular density estimation · POWERtest log likelihood: 0.63 -> -0.50Hurt
use flowified MLP instead of Neural Spline Flowtabular density estimation · GAStest log likelihood: 13.02 -> 5.35Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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