AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Learning Tractable Probabilistic Models from Inconsistent Local Estimates

Shasha Jin, Vasundhara Komaragiri, Tahrima Rahman, Vibhav Giridhar Gogate

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Exact inference for probabilistic programs · 0 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
Refine cutset network Q with inconsistent local pairwise estimates (Algorithm 1)Chow-Liu tree · 20 benchmark datasets avg, 0% evidencenegative cross-entropy: -79.81 -> -64.03Improved
Refine Q with local estimatescutset network (CN) · 20 datasets avg, 0% evidencenegative cross-entropy: -75.14 -> -59.01Improved
Refine Q with local estimatesmixture of cutset networks · 20 datasets avg, 0% evidencenegative cross-entropy: -69.67 -> -55.43Improved
Refine Q with local estimatesCLT · 20 datasets avg, 50% evidencenegative cross-entropy: -61.67 -> -50.28Improved
Refine Q with local estimatesMCN · 20 datasets avg, 80% evidencenegative cross-entropy: -39.19 -> -30.19Improved
Refine Q with local estimatesMCN · movie, 0% evidencenegative cross-entropy: -64.99 -> -34.14Improved
Refine Q with local estimatesCN · nltcs-like small dataset msnbc, 0% evidencenegative cross-entropy: -6.99 -> -6.36Improved
Refine Q with local estimatesMCN · msnbc, 50% evidencenegative cross-entropy: -5.03 -> -2.14Improved
Increase perturb rate h of initial network Q (ablation)Q vs R · movie (Figure 2)negative cross-entropyMixed
Increase noise std sigma on local statistics (ablation)R · pumsb* (Figure 3)negative cross-entropyHurt
Use sigma above 0.2 for local-statistic noise (ablation)R vs Q · pumsb*negative cross-entropyMixed
Increase number of evidence variables from 50% to 80% (ablation)Algorithm 1 · 20 datasets avgrelative improvement of R over QNo clear effect

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