AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Cardinality-Regularized Hawkes-Granger Model

Tsuyoshi Ide, Georgios Kollias, Dzung T. Phan, Naoki Abe

NeurIPS 2021 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 3 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 cMLP with L0Hawkes for Granger causal graph recovery from event dataGranger causality models · Sparse5 syntheticbreak-even accuracy: 0.31 ± 0.10 -> 1.00 ± 0.11Improved
replace cLSTM with L0Hawkes for Granger causal graph recovery from event dataGranger causality models · Sparse5 syntheticbreak-even accuracy: 0.43 ± 0.09 -> 1.00 ± 0.11Improved
replace cMLP with L0Hawkes to reduce training timeGranger causality models · Sparse5 syntheticcomputation time per parameter set (s): 881 -> 46Improved
replace cLSTM with L0Hawkes to reduce training timeGranger causality models · Sparse5 syntheticcomputation time per parameter set (s): 382 -> 46Improved
vary regularization tau over 0.5, 1, 2 and window w over 1, 2, 5, 10, 20 (ablation)L0Hawkes vs cLSTM/cMLP · Sparse5 syntheticbreak-even accuracyNo clear effect
use L0Hawkes instead of L1 or L2,1 regularization for sparsityHawkes-Granger model · Dense10 syntheticexact sparsity of AImproved
use L0Hawkes instead of L1 or L2,1 on power grid dataHawkes-Granger model · Grid (PMU failures)sparsity of AImproved

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