Newest papers

Residual-Based Causal Discovery via Pretrained In-Context Quantile Regression

Daniel Klippert, Huynh Quang Nhat, Alexander Marx · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29530 · cited by 0 works (OpenAlex) · open-access PDF

Korean

각 변수는 부모와 독립적 인 소음 소스 원천에서 생성된다고 가정한다. 이 변수는 이러한 소음을 추정하고 후보 원인에 대한 독립성을 테스트합니다. 추가 소음 모델 (ANM) 및 위치 규모의 소음 모델 (LSNM)의 더 넓은 클래스와 같은 식별 가능한 기능을 위해이 원칙은 원인 방향을 식별하지만, 원인 모델만이 이러한 독립성을 인정합니다. 기존의 LSNM 방법은 표준화 된 잔류물을 얻기 위해 파라미터적 가정에 의존합니다. 대조적으로, RESIT 프레임 워크는 폐기물의 비 파라미터적 추정을 허용하여 iteratively sink nodes를 식별하지만 ANMs에 대해 제안되었습니다. 이 격차를 닫기 위해, 우리는

Machine translation (Meta M2M100); the English original follows.

Abstract

Residual-based causal discovery assumes that each variable is generated from its parents and an independent noise source. It estimates this noise and tests its independence from candidate causes. For identifiable functions such as additive-noise models (ANMs) and the broader class of location-scale noise models (LSNMs), this principle identifies the causal direction, as only the causal model admits this independence. Existing LSNM methods rely on parametric assumptions to obtain standardized residuals, risking model misspecification. In contrast, the RESIT-framework allows for nonparametric estimation of residuals to iteratively identify sink nodes, but was proposed for ANMs. To close this gap, we propose Loscar, an extension of RESIT to LSNMs that estimates the conditional mean and scale via quantile regression, enabling pretrained tabular foundation models as plug-in estimators. We compare it with a feasible generalized least squares (FGLS) variant, which is consistent given suitable basis functions. Across bivariate and multivariate causal-discovery benchmarks, in-context quantile regression substantially outperforms FGLS with flexible function classes, particularly for multivariate causes.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Quantile, Bivariate analysis, Mathematics, Nonparametric statistics, Conditional independence, Econometrics

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange