Research map / Probabilistic and scientific modeling / Variational and generative sampling
Co-Generation with GANs using AIS based HMC
Tiantian Fang, Alexander Schwing
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 |
|---|---|---|---|
| Use AIS-based HMC instead of gradient descent | GAN co-generation · CelebA | MSSIM | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation · CelebA | MSE | Improved |
| Use AIS-based HMC instead of gradient descent with 5,000 initializations | GAN co-generation · LSUN | MSSIM | Improved |
| Use AIS-based HMC instead of gradient descent with 5,000 initializations | GAN co-generation · LSUN | MSE | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation · CelebA-HQ SISR | MSSIM | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation · CelebA-HQ SISR | MSE | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation · Synthetic 2D mixture | reconstruction error | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation · Synthetic ambiguous-mode reconstruction | reconstruction accuracy | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation with WGAN-GP · Synthetic 2D mixture | reconstruction accuracy | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation · LSUN test data | MSSIM | Improved |
| Use AIS-based HMC instead of gradient descent | GAN co-generation · LSUN test data | MSE | Improved |
Closest papers by meaning
- Metropolis-Hastings Generative Adversarial Networks (ICML 2019 · similarity 0.87)
- CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning (AAAI 2023 · similarity 0.86)
- CoT: Cooperative Training for Generative Modeling of Discrete Data (ICML 2019 · similarity 0.86)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.86)
- Variational Annealing of GANs: A Langevin Perspective (ICML 2019 · similarity 0.85)
- Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution (ICML 2024 · similarity 0.84)
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.
