Research map / Probabilistic and scientific modeling / Variational and generative sampling
Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks
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 |
|---|---|---|---|
| train DGN with exact EM instead of VAE amortized variational inference | deep generative network (2-layer, width 8) · noisy 2D circle dataset | negative log-likelihood | Helped |
| vary VAE learning rate (0.005, 0.001, 0.0001) (ablation) | VAE · noisy 2D circle dataset | negative log-likelihood | No clear effect |
| train with EM instead of VAE | DGN with latent dimension 1 · cosine-segment manifold and MNIST digit 4 | manifold fit quality | Helped |
| use Gaussian variational distribution in VAE for DGN posterior (ablation) | VAE · noisy circle 2D | KL between variational and true posterior | Hurt |
Closest papers by meaning
- From Variational to Deterministic Autoencoders (ICLR 2020 · similarity 0.89)
- InfoVAE: Balancing Learning and Inference in Variational Autoencoders (AAAI 2019 · similarity 0.89)
- Variational Laplace Autoencoders (ICML 2019 · similarity 0.89)
- Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis (ICLR 2025 · similarity 0.87)
- Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution (ICML 2024 · similarity 0.87)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 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.