SyPI+ extends SyPI to nonlinear time series via distance-correlation lag selection and a pruning step, reporting better F-score and SHD than PCMCI and CD-NOTS on synthetic data.
Causal discovery from nonstationary time series
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Causal Discovery for Autoregressive Time Series
SyPI+ extends SyPI to nonlinear time series via distance-correlation lag selection and a pruning step, reporting better F-score and SHD than PCMCI and CD-NOTS on synthetic data.