Pith. sign in

REVIEW 10 cited by

Kernel-based Conditional Independence Test and Application in Causal Discovery

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1202.3775 v1 pith:7FFPSW3Q submitted 2012-02-14 cs.LG stat.ML

Kun Zhang , Jonas Peters , Dominik Janzing , Bernhard Schoelkopf This is my paper · ORCID
classification cs.LGstat.ML
keywords conditionalindependencetestcausaldiscoveryespeciallykernel-basedlarge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Conditional independence testing is an important problem, especially in Bayesian network learning and causal discovery. Due to the curse of dimensionality, testing for conditional independence of continuous variables is particularly challenging. We propose a Kernel-based Conditional Independence test (KCI-test), by constructing an appropriate test statistic and deriving its asymptotic distribution under the null hypothesis of conditional independence. The proposed method is computationally efficient and easy to implement. Experimental results show that it outperforms other methods, especially when the conditioning set is large or the sample size is not very large, in which case other methods encounter difficulties.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Asymptotics of Nonparametric Estimation under General Non-monotone MAR Missingness: A Nonparametric Maximum Likelihood Approach

    stat.ME 2026-08 conditional novelty 8.0 of 10

    A sieve maximum likelihood estimator attains near-minimax Hellinger rates for density estimation under general non-monotone missing at random, with missingness affecting only the constant.

  2. Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparison

    stat.ML 2026-07 reject novelty 6.0 of 10

    DKMD is an antisymmetric kernel statistic for univariate distributions that reports the direction of a shift and can be computed in O(N log N), but the paper's consistency and robustness claims are not supported by it...

  3. CRT*: Conditional Randomization Testing with Heterogeneous External and Unlabeled Data

    stat.ME 2026-07 conditional novelty 6.0 of 10

    CRT* adaptively fuses internal, external, and unlabeled data via transfer learning and smooth residual bootstrap to give valid and more powerful conditional randomization tests under distributional heterogeneity.

  4. Causal Evidence for the Primordiality of Colors in Trans-Neptunian Objects

    astro-ph.EP 2025-07 reject novelty 6.0 of 10

    Causal analysis of 229 Trans-Neptunian Objects finds that orbital inclination does not cause color, which the authors interpret as evidence that TNO colors are primordial.

  5. Score-based Generative Modeling for Conditional Independence Testing

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A conditional independence test generates null samples via sliced score matching and Langevin dynamics, adds a goodness-of-fit check, and gives an asymptotic Type I error bound.

  6. Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis

    cs.LG 2025-01 conditional novelty 6.0 of 10

    CaDRe jointly recovers latent dynamic processes and observed causal graphs from time-series data, with identifiability theory and competitive climate forecasting.

  7. Fast Causal Discovery by Approximate Kernel-based Generalized Score Functions with Linear Computational Complexity

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A low-rank approximation of kernel-based generalized score functions reduces the computation and memory cost of score-based causal discovery to linear in sample size with comparable accuracy.

  8. Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    Empirical evaluation on synthetic and real-world datasets indicates that natural experiments are present and can be leveraged via causal feature selection to boost model performance.

  9. A Sample Efficient Conditional Independence Test in the Presence of Discretization

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A GMM-based conditional independence test (DCT-GMM) estimates latent Gaussian correlations from discretized data without binarizing, improving power over the prior DCT test.

  10. Causal Adjacency Learning for Spatiotemporal Prediction Over Graphs

    cs.LG 2024-11 reject novelty 4.0 of 10

    Using SyPI time-series causal discovery to build an adjacency matrix improves out-of-distribution mobility forecasts compared to fixed baselines, but the evaluation lacks sparsity controls and error bars.

Pith tools