AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Cooperative Graphical Models

Josip Djolonga, Stefanie Jegelka, Sebastian Tschiatschek, Andreas Krause

NeurIPS 2016 · Learning theory and algorithms › Sample complexity · approach: Computational thresholds in graphs and structure · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use tree-reweighted BP (TRWBP) inside the convex upper bound instead of mean-field/BP for the lower boundCooperative graphical models upper bound · Synthetic complete-graph experimentsmarginal error and log-partition estimateImproved
Use SDP relaxation for the upper bound instead of TRWBPCooperative graphical models upper bound · Synthetic complete-graph experimentslog-partition estimate qualityHurt
Lower bound via mean-field or BP at strong pairwise strength (beta large relative to alpha)Cooperative graphical models lower bound · Synthetic complete-graph experimentsbound and marginal qualityHurt
Exact MAP solver (epmap) instead of approximate MAP in perturb-and-MAP (ablation)pmap sampling approximation · Synthetic complete-graph experimentsmarginal errorNo clear effect
Use TRWBP instead of perturb-and-MAP (pmap) for marginalsCooperative graphical models on synthetic data · Synthetic complete-graph experiments, mixed vs strong pairwise interactionsmarginal errorMixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy