AI Paper Atlas

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

Can Push-forward Generative Models Fit Multimodal Distributions?

Antoine Salmona, Valentin De Bortoli, Julie Delon, Agnès Desolneux

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 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 a direct Lipschitz push-forward with a constrained Lipschitz constant to model separated modesVAEs and GANs · Balanced two-Gaussian mixturesdistribution fitHurt
Use a VAE decoder rather than a GAN generatorVAE and GAN · Univariate balanced two-Gaussian mixtureinterpolation between modesMixed
Use a score-based generative model instead of a direct push-forward modelVAE and GAN · Univariate balanced two-Gaussian mixturegeneration of separated modesImproved
Apply spectral normalization to the generator (ablation)GAN · Univariate multimodal mixturemode coverageHurt
Increase the targeted generator Lipschitz constant with gradient penalty (ablation)GAN · Univariate multimodal mixturemode coverage and mode collapseMixed
Increase the depth of the decoder (ablation)VAE · Univariate balanced two-Gaussian mixturedecoder Lipschitz constantImproved
Increase model size by adding depth (ablation)GAN · Univariate balanced two-Gaussian mixturetraining stabilityHurt
Add additive ResNet skip connections (ablation)GAN · Univariate balanced two-Gaussian mixturetraining stabilityImproved
Use more expressive ResNet or DenseNet decoder architectures (ablation)VAE and GAN · Univariate balanced two-Gaussian mixturegenerator Lipschitz constantNo clear effect
Use a score-based model instead of a direct push-forward modelVAE and GAN · MNIST-derived Gaussian mixtureinterpolation between modesImproved
Use a score-based model instead of a direct push-forward modelVAE and GAN · MNIST 3-and-7 subsetrecovery of distribution structureMixed

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