AI Paper Atlas

Research map / Image generation / GANs

Generative Bayesian Inference with GANs

Yuexi Wang, Veronika Rockova

JMLR 2026 · Image generation › GANs · approach: Generative adversarial network theory

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 the two-step proposal refinement (B-GAN-2S)B-GAN · Lotka-Volterra theta1=0.01posterior mean bias: 0.30 -> 0.08Improved
add the two-step proposal refinement (B-GAN-2S)B-GAN · Lotka-Volterra theta1=0.0195% CI width: 1.34 -> 0.28Improved
add variational Bayes regularization (B-GAN-VB)B-GAN · Lotka-Volterra theta1=0.0195% CI width: 1.34 -> 0.25Improved
add the two-step proposal refinement (B-GAN-2S)B-GAN · Boom-and-Bust kappa=5095% CI width: 11.00 -> 4.33Improved
add variational Bayes regularization (B-GAN-VB)B-GAN · Boom-and-Bust r=0.4posterior mean bias (x10^-1): 0.44 -> 0.24Improved
add variational Bayes regularization (B-GAN-VB)B-GAN · Lotka-Volterra theta2=0.5PMC: 0.33 -> 0.64Improved
use B-GAN-VB instead of SNLB-GAN-VB · Lotka-Volterra theta1=0.0195% CI width: 0.44 -> 0.25Improved
use B-GAN-VB instead of SNLB-GAN-VB · Boom-and-Bust alpha=0.1posterior mean bias (x10^-2): 1.01 -> 1.05No clear effect
use B-GAN-VB instead of ABC with summary statistics (SS)B-GAN-VB · Lotka-Volterra theta1=0.01posterior mean bias: 0.96 -> 0.08Improved
use B-GAN-VB instead of 2-Wasserstein ABC (W2)B-GAN-VB · Boom-and-Bust kappa=50posterior mean bias: 10.16 -> 1.56Improved
use B-GAN-2S instead of B-GAN-VBB-GAN-2S · Boom-and-Bust kappa=50posterior mean bias: 1.56 -> 1.42Mixed
build network on summary statistics instead of raw time seriesB-GAN · Boom-and-Bustposterior qualityImproved

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