Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational Message Passing with Structured Inference 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 |
|---|---|---|---|
| Use SAN instead of SVAE | Latent GMM · Pinwheel | training performance | Helped |
| Use SAN instead of GMM | Latent GMM · Pinwheel | performance | Helped |
| Use SAN instead of SVAE | Latent GMM · Pinwheel | performance upon convergence | No clear effect |
| Use SAN instead of VAE | Latent GMM · Auto | training performance | Helped |
| Use SAN instead of GMM | Latent GMM · Auto | performance | Helped |
| Use a Student's t-mixture generative model with a Gaussian structured inference network instead of a GMM | SAN · Pinwheel with outliers | test MSE | Helped |
| Use latent TMM instead of latent GMM under increasing outlier noise | SAN · Pinwheel with outliers | test MSE | Helped |
| Use SAN instead of LDS | Latent LDS · Dot | prediction error | Helped |
| Use SAN instead of SVAE | Latent LDS · Dot | prediction error | No clear effect |
Closest papers by meaning
- Iterative Amortized Inference (ICML 2018 · similarity 0.90)
- Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders (CVPR 2022 · similarity 0.89)
- Semi-Amortized Variational Autoencoders (ICML 2018 · similarity 0.89)
- Automatic variational inference with cascading flows (ICML 2021 · similarity 0.89)
- Deep Attentive Variational Inference (ICLR 2022 · similarity 0.89)
- Inference Suboptimality in Variational Autoencoders (ICML 2018 · similarity 0.88)
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.