AI Paper Atlas

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

Generative Flows with Matrix Exponential

Changyi Xiao, Ligang Liu

ICML 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 2 citations (OpenAlex)

Read the paper

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 matrix exponential coupling instead of affine coupling (ablation)MEF · CIFAR10bits/dim: 3.336$ \pm $ 0.002 -> 3.324$ \pm $ 0.004Improved
Use learning rate 0.01 instead of 0.001 (ablation)MEF with matrix exponential coupling · CIFAR10bits/dim: 3.381$ \pm $ 0.008 -> 3.324$ \pm $ 0.004Improved
Use matrix exponential 1×1 convolution instead of standard 1×1 convolution (ablation)MEF · CIFAR10bits/dim: 3.324$ \pm $ 0.001 -> 3.324$ \pm $ 0.004No clear effect
Use matrix exponential 1×1 convolution instead of standard 1×1 convolution (ablation)MEF · CIFAR10epoch time: 844.3$ \pm $ 2.6s -> 669.5$ \pm $ 10.1sImproved
Use matrix exponential 1×1 convolution instead of PLU decomposition convolution (ablation)MEF · CIFAR10bits/dim: 3.330$ \pm $ 0.007 -> 3.324$ \pm $ 0.004No clear effect
Use matrix exponential 1×1 convolution instead of PLU decomposition convolution (ablation)MEF · CIFAR10epoch time: 668.3$ \pm $ 19.6s -> 669.5$ \pm $ 10.1sNo clear effect
Use MEF instead of GlowGenerative flow density estimation · CIFAR10bits/dim: 3.35 -> 3.32Improved
Use MEF instead of Flow++ with variational dequantizationGenerative flow density estimation · CIFAR10bits/dim: 3.08 -> 3.32Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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