Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational Bayes on Monte Carlo Steroids
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 |
|---|---|---|---|
| add random parity-constraint projections (VB-MCS, k=5, median aggregation T=3) | sigmoid belief network with neural inference network · Caltech 101 Silhouettes | NLL (lower better): 251.04 -> 245.60 | Helped |
| add random parity-constraint projections (VB-MCS, k=5/10/20) | sigmoid belief network with neural inference network · NIPS Proceedings | log-perplexity (lower better): 5009.79 -> 4919.35 (k=5), 4919.22 (k=10), 4920.71 (k=20) | Helped |
| increase number of parity constraints k from 5 to 20 (ablation) | k-SBN with VB-MCS · Caltech 101 Silhouettes | NLL (lower better): 245.60 (k=5) -> 248.79 (k=10) -> 256.60 (k=20) | Hurt |
| vary number of parity constraints k across 5, 10, 20 (ablation) | k-SBN with VB-MCS · NIPS Proceedings | log-perplexity (lower better): 4919.35 / 4919.22 / 4920.71 | No clear effect |
Closest papers by meaning
- Excess Risk Bounds for the Bayes Risk using Variational Inference in Latent Gaussian Models (NeurIPS 2017 · similarity 0.91)
- Importance Weighted Hierarchical Variational Inference (NeurIPS 2019 · similarity 0.91)
- Variational Learning of Fractional Posteriors (ICML 2025 · similarity 0.88)
- Forward $\chi^2$ Divergence Based Variational Importance Sampling (ICLR 2024 · similarity 0.88)
- Bayesian Online Natural Gradient (BONG) (NeurIPS 2024 · similarity 0.88)
- Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference (NeurIPS 2026 · 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.