AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Causal Component Analysis

Wendong Liang, Armin Kekić, Julius von Kügelgen, Simon Buchholz, Michel Besserve, Luigi Gresele, Bernhard Schölkopf

NeurIPS 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability

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 linear encoder instead of nonlinear encoder (ablation)CauCA model · synthetic CauCAMCCHurt
assume trivial graph with no arrows instead of the true causal graph (ablation)CauCA model · synthetic CauCAMCCHurt
increase signal-to-noise ratio of linear SCM parameters (more dependent latents) (ablation)CauCA vs trivial-graph baseline · synthetic CauCAmedian MCCImproved
increase number of nonlinear layers M in ground-truth mixing (ablation)CauCA model · synthetic CauCAMCCHurt
vary latent dimensionality (ablation)CauCA model · synthetic CauCAMCCNo clear effect
use interventional data and nonlinear flow instead of linear baselinenonlinear ICA model · synthetic ICAMCCImproved
train naive single-environment flow on pooled data ignoring interventions (ablation)normalizing flow · synthetic ICAMCCHurt

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