AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay

Frederic Koehler

NeurIPS 2019 · Graph learning › Graph algorithms and clustering · approach: Continuous DAG structure learning · 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
Initialize mean-field iteration at the all-ones vectorMean-field iteration for ferromagnetic Ising models · Arbitrary ferromagnetic Ising modelsmean-field free-energy gap: 0 ≤ Φ_MF(x*) − Φ_MF(x_t) ≤ min{(||J||_1 + ||h||_1)/t, 2((||J||_1 + ||h||_1)/t)^(4/3)}Improved
Initialize BP messages to all onesBelief propagation for ferromagnetic Ising models · Arbitrary graphs with m edgesBethe free-energy gap: 0 ≤ ΦBethe(P*) − Φ*Bethe(ν(t)) ≤ √(8mn(1 + ||J||∞)/t)Improved
Use near-zero rather than all-ones initial messages (ablation)Belief propagation · Ferromagnetic Ising modelsconvergence rateHurt

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