AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Causal normalizing flows: from theory to practice

Adrián Javaloy, Pablo Sanchez Martin, Isabel Valera

NeurIPS 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 5 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 causal NF (abductive, L=1) instead of CAREFL with do-operatorCAREFL · Triangle NLINcounterfactual RMSE: 0.17_{0.03} -> 0.13_{0.02}Improved
use causal NF instead of CAREFLCAREFL · Large backdoor NLINATE RMSE: 0.05_{0.01} -> 0.02_{0.00}Improved
use causal NF instead of CAREFLCAREFL · Large backdoor NLINcounterfactual RMSE: 0.08_{0.01} -> 0.01_{0.00}Improved
use causal NF instead of CAREFLCAREFL · Simpson SYMPRODATE RMSE: 0.10_{0.02} -> 0.07_{0.01}Improved
use causal NF instead of CAREFLCAREFL · Large backdoor NLINsampling time (microseconds): 8.25_{1.29} -> 3.05_{0.66}Improved
use causal NF instead of VACAVACA · Triangle NLINKL divergence: 7.71_{0.60} -> 0.00_{0.00}Improved
use causal NF instead of VACAVACA · Large backdoor NLINtraining time (microseconds): 164.92_{11.10} -> 0.52_{0.10}Improved
use causal NF instead of CAREFLCAREFL · Large backdoor NLINKL divergence: 1.51_{0.05} -> 1.51_{0.04}No clear effect
use abductive instead of generative network design (ablation)causal NF · 4-chain SCMKL divergence, ATE, counterfactual RMSEImproved
embed causal graph in abductive architecture (ablation)causal NF · 4-chain SCMATE RMSEImproved
generative models with causal graph and fewer layers than diameter (L<3) (ablation)causal NF · 4-chain SCMKL divergenceHurt
add Jacobian regularization (ablation)abductive causal NF L=1 with graph · 4-chain SCMcausal consistencyNo clear effect

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