Research map / Image generation / GANs
Generative Bayesian Inference with GANs
Yuexi Wang, Veronika Rockova
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add the two-step proposal refinement (B-GAN-2S) | B-GAN · Lotka-Volterra theta1=0.01 | posterior mean bias: 0.30 -> 0.08 | Improved |
| add the two-step proposal refinement (B-GAN-2S) | B-GAN · Lotka-Volterra theta1=0.01 | 95% CI width: 1.34 -> 0.28 | Improved |
| add variational Bayes regularization (B-GAN-VB) | B-GAN · Lotka-Volterra theta1=0.01 | 95% CI width: 1.34 -> 0.25 | Improved |
| add the two-step proposal refinement (B-GAN-2S) | B-GAN · Boom-and-Bust kappa=50 | 95% CI width: 11.00 -> 4.33 | Improved |
| add variational Bayes regularization (B-GAN-VB) | B-GAN · Boom-and-Bust r=0.4 | posterior mean bias (x10^-1): 0.44 -> 0.24 | Improved |
| add variational Bayes regularization (B-GAN-VB) | B-GAN · Lotka-Volterra theta2=0.5 | PMC: 0.33 -> 0.64 | Improved |
| use B-GAN-VB instead of SNL | B-GAN-VB · Lotka-Volterra theta1=0.01 | 95% CI width: 0.44 -> 0.25 | Improved |
| use B-GAN-VB instead of SNL | B-GAN-VB · Boom-and-Bust alpha=0.1 | posterior mean bias (x10^-2): 1.01 -> 1.05 | No clear effect |
| use B-GAN-VB instead of ABC with summary statistics (SS) | B-GAN-VB · Lotka-Volterra theta1=0.01 | posterior mean bias: 0.96 -> 0.08 | Improved |
| use B-GAN-VB instead of 2-Wasserstein ABC (W2) | B-GAN-VB · Boom-and-Bust kappa=50 | posterior mean bias: 10.16 -> 1.56 | Improved |
| use B-GAN-2S instead of B-GAN-VB | B-GAN-2S · Boom-and-Bust kappa=50 | posterior mean bias: 1.56 -> 1.42 | Mixed |
| build network on summary statistics instead of raw time series | B-GAN · Boom-and-Bust | posterior quality | Improved |
Closest papers by meaning
- Bayesian GAN (NeurIPS 2017 · similarity 0.92)
- Implicit Variational Inference for High-Dimensional Posteriors (NeurIPS 2023 · similarity 0.90)
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks (ICML 2017 · similarity 0.89)
- GATSBI: Generative Adversarial Training for Simulation-Based Inference (ICLR 2022 · similarity 0.89)
- Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs (ICML 2019 · similarity 0.88)
- VIKING: Deep variational inference with stochastic projections (NeurIPS 2025 · similarity 0.87)
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.
