Order-Agnostic Autoregressive Modelling with Missing Data

Order-Agnostic autoregressive models have shown strong capabilities in deep generative modeling, yet their application in scenarios with incomplete data has been underexplored. This research reinterprets these models through the lens of missing data, demonstrating that standard training procedures on fully observed data perform implicit imputation under a missing completely at random mechanism, leading to effective out-of-sample imputation in high missingness settings.

The introduction of a principled framework for training these models on incomplete datasets signifies a major advancement in the field of artificial intelligence. This development not only enhances the robustness of predictive modeling in real-world applications but also opens avenues for active information acquisition, allowing for more informed decision-making in data-driven environments.