AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Frequency-Domain Better than Time-Domain for Causal Structure Recovery in Dynamical Systems on Networks

Mohammed Tuhin Rana, Mishfad Shaikh Veedu, James Melbourne, Murti Salapaka

ICLR 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Causal effect identification

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
estimate Wiener filters in frequency domain (FFT) instead of time domainW-PC · 25 random networks (large samples)computation time: around an order of magnitude lowerImproved
estimate Wiener filters in frequency domain instead of time domainW-PC · 25 random 6-node DAGsaverage error rateImproved
use frequency-domain estimation instead of time-domainW-PC · 25 random 6-node DAGssamples neededImproved
use Wiener phase information in frequency domainWiener Phase vs TD W-PC · 25 random 6-node DAGsaverage error rateImproved
use FFT-WPC instead of TPCtime-series causal discovery · 20 nodes syntheticF1 (%) and run time (s): 78.57 -> 100; 4016.57 -> 1011.62Improved
use Wiener Phase instead of TPCtime-series causal discovery · 20 nodes syntheticrun time (s): 4016.57 -> 1.37Improved
use FFT-WPC instead of TPCtime-series causal discovery · River-runoff (real)run time (s): 1548.29 -> 9.041Improved
use Wiener Phase instead of FFT-WPCtime-series causal discovery · River-runoff (real)F1 (%): 75 -> 48.3Hurt
use Wiener Phase instead of GCtime-series causal discovery · River-runoff (real)F1 (%): 33 -> 48.3Improved
use Wiener Phase instead of FFT-WPCtime-series causal discovery · 50 nodes synthetic networkrun time (s): 142652 -> 19.49Improved
violate the phase alignment assumption (Wiener Phase) (ablation)Wiener Phase · 20 nodes, 128000 samplescombined score CS (%): 92.69No clear effect
use Wiener Phase and FFT-WPC instead of GC when present value depends on present valuetime-series causal discovery · 6-node zero-lag networkcombined score CS (%): 80 -> 100Improved

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