AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

Zhenyu Zhu, Francesco Locatello, Volkan Cevher

NeurIPS 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Constraint-based structure learning with latents · 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
increase C_m from 1 to 512 (ablation)SCORE with ReLU score network · d=100, n=100SHD: 2941.0±29.5 -> 13.8 ± 1.8Improved
increase C_m from 1 to 4 (ablation)SCORE with ReLU score network · d=100, n=100SHD: 2941.0±29.5 -> 2900.6 ± 80.8No clear effect
increase C_m from 16 to 64 (ablation)SCORE with ReLU score network · d=100, n=100SHD: 1512.4 ± 283.6 -> 55.0 ± 16.0Improved
increase C_m from 128 to 512 (ablation)SCORE with ReLU score network · d=100, n=100SHD: 23.9 ± 4.6 -> 13.8 ± 1.8Improved
increase number of samples n from 5 to 160 (ablation)SCORE with ReLU score network · d=10, C_m=1SHD: 31.7±2.1 -> 13.0± 4.0Improved
increase n from 20 to 40 (ablation)SCORE with ReLU score network · d=10, C_m=1SHD: 23.3±2.7 -> 23.0±4.0No clear effect
increase number of variables d from 5 to 100 (ablation)SCORE with ReLU score network · n=10, C_m=1SHD: 4.5 ± 2.0 -> 2923.7 ± 38.5Hurt
increase d from 10 to 20 (ablation)SCORE with ReLU score network · n=10, C_m=1SHD: 29.6 ± 2.2 -> 124.3 ± 4.6Hurt

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