AI Paper Atlas

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

A Non-Negative Deep VAE: The Generalized Gamma Belief Network

Zhibin Duan, Tiansheng Wen, Muyao Wang, Bo Chen, Hao Zhang, Bo Chen, Fei Meng, Hongwei Liu, Mingyuan Zhou

TPAMI 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 2 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
replace linear GBN decoder with non-linear generative networkGBN · 20NGperplexity: 678 -> 589Improved
replace linear GBN decoder with non-linear generative networkGBN · R8perplexity: 657 -> 385Improved
use gamma latents with Weibull posterior in place of Gaussian latentsVDVAE · MNISTNLL (nats): 78.07 -> 77.86Improved
use gamma latents with Weibull posterior in place of Gaussian latentsVDVAE · OMNIGLOTNLL (nats): 86.93 -> 86.04Improved
use gamma latents with Weibull posterior in place of Gaussian latentsVDVAE · CIFAR-10bits/dim: 2.87 -> 2.84Improved
use gamma latents with Weibull posterior in place of Gaussian latentsVDVAE · CELEBAbits/dim: 2.00 -> 1.95Improved
compare with Attention VAE (100 importance samples on CIFAR-10)Generalized GBN · MNISTNLL (nats): 77.63 vs 77.86Hurt
use sparse gamma latents instead of Gaussian latents without regularizerVAE · 3D Shapes (disentanglement)FactorVAE metric: 0.550 -> 0.841Improved
use sparse gamma latents instead of Gaussian latents without regularizerVAE · 3D Cars (disentanglement)FactorVAE metric: 0.753 -> 0.946Improved
use sparse gamma latents instead of Gaussian latents without regularizerVAE · 2D Shapes (disentanglement)FactorVAE metric: 0.617 -> 0.626Improved
compare gamma latents with BetaTCVAE regularized GaussianBetaTCVAE · 3D Shapes (disentanglement)FactorVAE metric: 0.974 vs 0.841Hurt
compare gamma latents with BetaTCVAE regularized GaussianBetaTCVAE · 3D Cars (disentanglement)FactorVAE metric: 0.929 -> 0.946Improved

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