Research map / Learning theory and algorithms / Sample complexity
Cooperative Graphical Models
Josip Djolonga, Stefanie Jegelka, Sebastian Tschiatschek, Andreas Krause
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 |
|---|---|---|---|
| Use tree-reweighted BP (TRWBP) inside the convex upper bound instead of mean-field/BP for the lower bound | Cooperative graphical models upper bound · Synthetic complete-graph experiments | marginal error and log-partition estimate | Improved |
| Use SDP relaxation for the upper bound instead of TRWBP | Cooperative graphical models upper bound · Synthetic complete-graph experiments | log-partition estimate quality | Hurt |
| Lower bound via mean-field or BP at strong pairwise strength (beta large relative to alpha) | Cooperative graphical models lower bound · Synthetic complete-graph experiments | bound and marginal quality | Hurt |
| Exact MAP solver (epmap) instead of approximate MAP in perturb-and-MAP (ablation) | pmap sampling approximation · Synthetic complete-graph experiments | marginal error | No clear effect |
| Use TRWBP instead of perturb-and-MAP (pmap) for marginals | Cooperative graphical models on synthetic data · Synthetic complete-graph experiments, mixed vs strong pairwise interactions | marginal error | Mixed |
Closest papers by meaning
- Provable Variational Inference for Constrained Log-Submodular Models (NeurIPS 2018 · similarity 0.88)
- Variational Inference in Mixed Probabilistic Submodular Models (NeurIPS 2016 · similarity 0.88)
- Probabilistic Circuits for Variational Inference in Discrete Graphical Models (NeurIPS 2020 · similarity 0.87)
- Context-Aware Online Collective Inference for Templated Graphical Models (ICML 2021 · similarity 0.87)
- TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing (NeurIPS 2024 · similarity 0.86)
- Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data (NeurIPS 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.
