A kernel-copula embedding statistic equals zero exactly when causal dependence between X and Y is stable and is strictly positive otherwise, with a near-linear estimator and convergence rates provided.
arXiv preprint arXiv:2506.07760 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Detecting Changes in Causal Dependence with Kernels and Copulas
A kernel-copula embedding statistic equals zero exactly when causal dependence between X and Y is stable and is strictly positive otherwise, with a near-linear estimator and convergence rates provided.