Deep End-to-end Causal Inference and Introduction to Causal Discovery

Explore deep end-to-end causal inference and causal discovery in this comprehensive lecture from the Broad Institute's Models Inference and Algorithms series. Delve into the DECI framework, a flow-based method for causal discovery and inference, including conditional average treatment effect estimation. Learn how this framework applies to real-world data such as time series and scenarios with latent confounders. Discover the Microsoft causal AI suite's practical applications. Begin with a primer on causal discovery and inference, covering the causal hierarchy, structural equation models, Pearl's do-calculus, and methods for identifying causal relationships from observational data. Gain insights into bridging causality and deep learning for real-world impact in fields like business engagement, medical treatment, and policymaking.

MIA: Cheng Zhang and Nick Pawlowski, Deep End-to-end Causal Inference; Primer: Causal Discovery