Can I read Causal Discovery in Nonstationary Time Series on EtoBox?

Causal Discovery in Nonstationary Time Series by akshatbhatnagar797 is a document available to read on EtoBox.

What is Causal Discovery in Nonstationary Time Series about?

This paper addresses causal discovery and forecasting in nonstationary time series using state-space models, highlighting the challenges of traditional methods that assume fixed causal structures. It demonstrates that nonstationarity can aid in identifying causal relationships and improve forecasting accuracy by adapting to changes in causal strengths and noise variances. The authors propose a framework that allows for time-varying causal models and show through experiments that their approach effectively u

Author

akshatbhatnagar797

Language

EN