AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Truncated Matrix Power Iteration for Differentiable DAG Learning

Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi

NeurIPS 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: Randomized sketching for matrices · 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
replace Binomial DAG constraint with TMPIDAG-GNN · 50-node ER1 nonlinearSHD: 25.2 -> 22.2Improved
replace DAG constraint with TMPINOTEARS-MLP · 50-node ER1 MLP SEMSHD: 16.9 -> 14.9Improved
replace DAG constraint with TMPIDAG-GNN · SachsSHD: 16 -> 16No clear effect
replace DAG constraint with TMPIDAG-GNN · SachsSHDC: 21 -> 17Improved
replace DAG constraint with TMPIGran-DAG · SachsSHD: 13 -> 12Improved
replace DAG constraint with TMPIGran-DAG · SachsSHDC: 11 -> 9Improved
replace DAG constraint with TMPIGran-DAG++ · SachsSHD: 13 -> 12Improved
replace DAG constraint with TMPIGran-DAG++ · SachsSHDC: 10 -> 9Improved
replace Exponential constraint with TMPIGOLEM · 500-node ER2 GaussianSHD: 45.20 -> 14.45Improved
replace Binomial constraint with TMPIGOLEM · 500-node ER2 GaussianSHD: 46.75 -> 14.45Improved
replace Exponential constraint with TMPIGOLEM · 500-node ER2 Gaussianrunning time (s): 882.22 -> 670.26Improved
replace Binomial constraint with TMPIGOLEM · 500-node ER2 Gaussianrunning time (s): 795.24 -> 670.26Improved

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