PhD Defense of Shayan Shirahmadi Gale Bagi
February 21, 2025
I’m delighted to announce that Shayan Shirahmadi Gale Bagi had his PhD defense on Feb 3, 2025. The defense was successful and he has now submitted his thesis to the UWaterloo Library (Bagi, 2025). Congratulations Dr. Gale Bagi!
His thesis work was on theoretical and applied methods for improving our ability to learn latent causal relationships from observational data. This included a paper “Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting” at ICML in 2023 (Bagi et al., 2023).
In this paper, Shayan proposed a new framework for leveraging causal information to improve robustness of learning in the presence of distribution shift and included. Empirical results on the motion forecasting domain support the theoretical findings. Shayan also has more recent work available “ Implicit Causal Representation Learning via Switchable Mechanisms” as a preprint on Arxiv (Bagi et al., 2024).