Research map / Probabilistic and scientific modeling / Variational and generative sampling
Leveraging the Exact Likelihood of Deep Latent Variable Models
Pierre-Alexandre Mattei, Jes Frellsen
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 Metropolis-within-Gibbs instead of pseudo-Gibbs for imputation | Trained VAE · MNIST, OMNIGLOT, and Caltech Silhouettes; missing-at-random and top/bottom missing scenarios | F1 score | Improved |
| Use Metropolis-within-Gibbs instead of pseudo-Gibbs for imputation | Trained VAE · MNIST, OMNIGLOT, and Caltech Silhouettes; all tested missingness scenarios | Wilcoxon signed-rank p-value | Mixed |
| Constrain the Gaussian decoder covariance eigenvalues to be at least ξ = 2^{-4} | Gaussian DLVM · Frey Faces | generalisation performance | Mixed |
Closest papers by meaning
- Latent variable model for high-dimensional point process with structured missingness (ICML 2024 · similarity 0.87)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 2025 · similarity 0.86)
- Identifying Metric Structures of Deep Latent Variable Models (ICML 2025 · similarity 0.85)
- DiffPuter: Empowering Diffusion Models for Missing Data Imputation (ICLR 2025 · similarity 0.85)
- Forward $\chi^2$ Divergence Based Variational Importance Sampling (ICLR 2024 · similarity 0.85)
- Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors (AAAI 2025 · similarity 0.85)
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.
