Research map / Probabilistic and scientific modeling / Variational and generative sampling
Contrastive Divergence Learning is a Time Reversal Adversarial Game
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CD with Langevin dynamics and no correction for finite-step inexactness (ablation) | CD · 10D spiral toy density | density estimation quality | Hurt |
| Correct inexact Langevin transitions with Metropolis-Hastings rejection (ablation) | CD · 10D spiral toy density | density estimation quality | Helped |
| Weight each chain's update by its hardness instead of using Metropolis-Hastings rejection (ablation) | CD · 10D spiral toy density | density estimation quality | Helped |
| Use a large-variance Gaussian contrastive distribution (ablation) | CNCE · 10D spiral toy density | density estimation quality | Hurt |
| Use a small-variance Gaussian contrastive distribution (ablation) | CNCE · 10D spiral toy density | density estimation quality | Hurt |
| Adapt the contrastive distribution to the current model using its reversible MCMC transition (ablation) | CNCE · 10D spiral toy density | density estimation quality | Helped |
Closest papers by meaning
- Approximation and Convergence Properties of Generative Adversarial Learning (NeurIPS 2017 · similarity 0.88)
- Near-Optimality of Contrastive Divergence Algorithms (NeurIPS 2024 · similarity 0.88)
- Bridging Maximum Likelihood and Adversarial Learning via α-Divergence (AAAI 2020 · similarity 0.87)
- Improved Contrastive Divergence Training of Energy-Based Models (ICML 2021 · similarity 0.87)
- Deep MMD Gradient Flow without adversarial training (ICLR 2025 · similarity 0.86)
- CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models (ICML 2025 · similarity 0.86)
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.