AI Paper Atlas

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

Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation

Tahrima Rahman, Shasha Jin, Vibhav Gogate

ICML 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Latent variable marginalization and estimators · 4 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
learn cutset network with latent-model compilation (CNxD) instead of from data alone (CN)cutset networks · 20 density datasetsaverage test log-likelihood: -57.05 -> -55.40Improved
learned structure (CNxD) instead of random deep structure (CNR) (ablation)cutset networks · 20 density datasetsaverage test log-likelihood: -62.81 -> -55.40Improved
CNxD versus ACBNCNxD · 20 density datasetstest log-likelihood: -56.10 -> -55.40Improved
CNxD versus ACMNCNxD · 20 density datasetstest log-likelihood: -55.78 -> -55.40Mixed
CNxD versus PSDDCNxD · 20 density datasetstest log-likelihood: -59.06 -> -55.40Improved
CNxD versus latent models MT and BCNCNxD · 20 density datasetsaverage test log-likelihood: -55.33 -> -55.40 ; BCN -53.91Hurt
CNxD versus CN for MAP at 20% evidenceCNxD · MAP completionavg oracle log-likelihood: -26.48 -> -25.65Improved
CNxD versus CN for MAP at 50% evidenceCNxD · MAP completionavg oracle log-likelihood: -38.77 -> -37.91Improved
CNxD versus CN for MAP at 80% evidenceCNxD · MAP completionavg oracle log-likelihood: -44.19 -> -43.65Improved
exact MAP on CNxD versus approximate marginal MAP on MTCNxD · MAP completion 20% evidenceavg oracle log-likelihood: -27.82 -> -25.65Improved
exact MAP on CNxD versus approximate marginal MAP on BCNCNxD · MAP completion 50% evidenceavg oracle log-likelihood: -39.36 -> -37.91Improved
increase depth of CNxD (ablation)CNxD · density estimation vs running timetest log-likelihoodImproved

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