analiza aiqbench
Causal-TS introduces four specialized algorithms designed to handle high-dimensional and nonstationary time series, addressing critical challenges in modeling dynamic systems where standard methods often fail due to structural breaks. By integrating GPU acceleration via PyTorch with a unified conditional independence test layer, the library offers an efficient end-to-end pipeline for discovering causal structures from raw data to effect estimates. This tool represents significant progress in machine learning methodology by enabling robust analysis of complex temporal dependencies that evolve over time.
Causal-TS: A Python Library for Causal Discovery in High-Dimensional and Nonstationary Time Series
arXiv:2607.24673v1 Announce Type: new Abstract: We describe Causal-TS, an open-source Python library for causal discovery in high-dimensional and nonstationary multivariate time series. Causal-TS provides four specialized algorithms-CDNOTS, CDNOTS+, CEDAR, and GRACE-along with wrappers for GES, Granger, LASSO-VAR, and LGES, all sharing a unified conditional independence (CI) test layer with GPU acceleration via PyTorch. A regime discovery pipeline detects structural breaks via pluggable changepoint detectors and runs discovery per regime with regime-specific parameters. A command-line interface, synthetic data generators, and optional DoWhy integration provide an end-to-end pipeline from raw time series to causal effect estimates. The library is pip-installable, tested on Python 3.10--3.12, and available at https://github.com/bloomberg/causal-ts.
Abstract:We describe Causal-TS, an open-source Python library for causal discovery in high-dimensional and nonstationary multivariate time series. Causal-TS provides four specialized algorithms-CDNOTS, CDNOTS+, CEDAR, and GRACE-along with wrappers for GES, Granger, LASSO-VAR, and LGES, all sharing a unified conditional independence (CI) test layer with GPU acceleration via PyTorch. A regime discovery pipeline detects structural breaks via pluggable changepoint detectors and runs discovery per regime with regime-specific parameters. A command-line interface, synthetic data generators, and optional DoWhy integration provide an end-to-end pipeline from raw time series to causal effect estimates. The library is pip-installable, tested on Python 3.10--3.12, and available at this https URL.
Machine Learning (cs.LG); Methodology (stat.ME)
arXiv:2607.24673 [cs.LG]
(or arXiv:2607.24673v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.24673 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 199 cuvinte
Subiecte conexe
Links #3: 2026/06 Part 1
LessWrong · 15 iun. 2026
NVIDIA CUDA 13.3 Enhances GPU Development with Tile Programming in C++, Compiler Autotuning, and Python Updates
NVIDIA · 26 mai 2026
CASC: Causal Adversarial Subspace Clustering for Multivariate Spatiotemporal Data
arXiv · 24 iul. 2026
News
Quantum Computing Report · 7 iun. 2026