AI Paper Atlas

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

Invertible Monotone Operators for Normalizing Flows

Byeongkeun Ahn, Chiyoon Kim, Youngjoon Hong, Hyunwoo J. Kim

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Normalizing flow training and design · 3 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
Add monotone formulation (replace residual connections) (ablation)i-DenseNet-style flow with CPila · CIFAR-10bpd: 3.243 -> 3.215Improved
Add CPila activation (replace CLipSwish) (ablation)Monotone Flow · CIFAR-10bpd: 3.229 -> 3.215Improved
Add monotone formulation and CPila to i-DenseNet (ablation)i-DenseNet · CIFAR-10bpd: 3.252 -> 3.215Improved
Add learnable scaling to 2 residual blocks (ablation)2 RBs · Toy 1DMSE: 1.6\times10^{-2} -> 5.8\times10^{-3}Improved
Replace residual blocks with monotone blocks (ablation)2 RBs w/ LS · Toy 1DMSE: 5.8\times10^{-3} -> 7.6\times10^{-5}Improved
Use inverse residual block as second layer instead of residual (ablation)2 RBs w/ LS · Toy 1DMSE: 5.8\times10^{-3} -> 4.5\times10^{-3}No clear effect
Monotone Flow vs Residual FlowMonotone Flow · MNISTbpd: 0.97 -> 0.928Improved
Monotone Flow vs i-DenseNetMonotone Flow · CIFAR-10bpd: 3.25 -> 3.215Improved
Monotone Flow vs i-DenseNetMonotone Flow · ImageNet32bpd: 3.98 -> 3.961Improved
Monotone Flow vs Residual FlowMonotone Flow · ImageNet64bpd: 3.76 -> 3.734Improved
Add variational dequantizationMonotone Flow · CIFAR-10bpd: 3.215 -> 3.062Improved
Add variational dequantizationMonotone Flow · ImageNet32bpd: 3.961 -> 3.901Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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