Research map / Probabilistic and scientific modeling / Variational and generative sampling
Gauging Variational Inference
Sung-Soo Ahn, Michael Chertkov, Jinwoo Shin
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 |
|---|---|---|---|
| Optimize gauges jointly with the product distribution | Mean-field · Generic graphical models | lower bound on log partition function | Improved |
| Constrain gauge-transformed factors to be nonnegative | Belief propagation gauge optimization · General graphical models | lower bound on log partition function | Improved |
| Apply Gauged-BP sequentially to residual partition functions (ablation) | Gauged-BP · Complete graphical models | log-partition approximation error | Improved |
| Include multiple configurations differing from the all-zero configuration (ablation) | Gauged-BP · Complete graphical models | log-partition approximation error | Improved |
| Use sequential residual-partition correction (ablation) | Gauged-BP · Large generic non-log-supermodular graphs | log(Z_LB/Z_MF): up-to e^{14} times | Improved |
| Use Gauged-BP-based algorithms | Mean-field and Gauged-MF · Large log-supermodular graphs | log(Z_LB/Z_MF): up to e^{25} times | Improved |
| Fix the product distribution to the all-zero configuration rather than optimizing it (ablation) | Gauged-MF · General graphical models | lower bound on log partition function | Hurt |
| Use the all-zero configuration as the fixed distribution (ablation) | Gauged-MF · Log-supermodular models | log(Z_LB/Z_MF) | Improved |
Closest papers by meaning
- Bucket Renormalization for Approximate Inference (ICML 2018 · similarity 0.87)
- Neural Variational Inference and Learning in Undirected Graphical Models (NeurIPS 2017 · similarity 0.87)
- Mean-Field Variational Inference via Wasserstein Gradient Flow (JMLR 2025 · similarity 0.87)
- Advances in Variational Inference (TPAMI 2018 · similarity 0.86)
- Spectral Approximate Inference (ICML 2019 · similarity 0.86)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · 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.
