Research map / Probabilistic and scientific modeling / Variational and generative sampling
Neural Variational Inference and Learning in Undirected Graphical Models
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 |
|---|---|---|---|
| Replace Ber(200) with an RBM(64,8) prior | VAE · Binarized MNIST test | negative log-likelihood: 111.9 -> 105.4 | Helped |
| Replace Ber(200) with an RBM(64,64) prior | VAE · Binarized MNIST test | negative log-likelihood: 111.9 -> 102.3 | Helped |
| Replace Ber(200) with an RBM(64,8) prior | ADGM · Binarized MNIST test | negative log-likelihood: 107.9 -> 104.3 | Helped |
| Replace Ber(200) with an RBM(64,64) prior | ADGM · Binarized MNIST test | negative log-likelihood: 107.9 -> 100.7 | Helped |
| Replace Ber(200) with an RBM(64,8) prior | VAE · Omniglot test | negative log-likelihood: 135.1 -> 130.2 | Helped |
| Replace Ber(200) with an RBM(64,64) prior | VAE · Omniglot test | negative log-likelihood: 135.1 -> 128.5 | Helped |
| Replace Ber(200) with an RBM(64,8) prior | ADGM · Omniglot test | negative log-likelihood: 136.8 -> 134.4 | Helped |
| Replace Ber(200) with an RBM(64,64) prior | ADGM · Omniglot test | negative log-likelihood: 136.8 -> 131.1 | Helped |
| Use an RBM prior instead of a Bernoulli prior | VAE and ADGM hybrid models · Binarized MNIST and Omniglot | negative log-likelihood | Mixed |
Closest papers by meaning
- Variational Inference for Sparse and Undirected Models (ICML 2017 · similarity 0.90)
- Probabilistic Circuits for Variational Inference in Discrete Graphical Models (NeurIPS 2020 · similarity 0.89)
- Black-box coreset variational inference (NeurIPS 2022 · similarity 0.89)
- Undirected Graphical Models as Approximate Posteriors (ICML 2020 · similarity 0.89)
- Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference (NeurIPS 2026 · similarity 0.87)
- Batch and match: black-box variational inference with a score-based divergence (ICML 2024 · 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.