AI Paper Atlas

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

Learning to Reason: Leveraging Neural Networks for Approximate DNF Counting

Ralph Abboud, Ismail Ceylan, Thomas Lukasiewicz

AAAI 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Exact inference for probabilistic programs · 22 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 8 message-passing iterations rather than 2 (ablation)NeuralDNF · Structure test setaccuracy at threshold 0.10: 91.36 -> 99.95Improved
Use 8 message-passing iterations rather than 2 (ablation)NeuralDNF · 10K-variable size generalizationaccuracy at threshold 0.10: 84.20 -> 97.13Improved
Use 8 message-passing iterations rather than 2 (ablation)NeuralDNF · 15K-variable size generalizationaccuracy at threshold 0.10: 79.31 -> 94.83Improved
Use 32 rather than 8 message-passing iterations (ablation)NeuralDNF · Structure test setaccuracy at threshold 0.10: 99.95 -> 99.83No clear effect
Use 32 rather than 8 message-passing iterations (ablation)NeuralDNF · 10K-variable size generalizationaccuracy at threshold 0.10: 97.13 -> 93.67Hurt
Use 32 rather than 8 message-passing iterations (ablation)NeuralDNF · 15K-variable size generalizationaccuracy at threshold 0.10: 94.83 -> 87.93Hurt
Use NeuralDNF instead of KLMWeighted DNF counting · 15K-variable formulas, width 3runtime (s): 2375.56 -> 0.104Improved

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