Hey, I’m Kia! I’m a DPhil student in the Department of Statistics at the University of Oxford, working with François Caron and Tom Rainforth. My research interests relate broadly to the following areas and questions:

• Scalable, reliable deep learning:
  • How can we reliably and efficiently quantify the uncertainty in neural network predictions?
• Generalization under distribution shifts:
  • How can we train models that generalize well in the presence of distribution shifts?
• Data-efficient learning:
  • How can we learn in situations where obtaining new data is expensive (active learning, semi-supervised learning)?

Previously, I worked on analyzing the quality of variational approximations to Bayesian neural networks with Mark van der Wilk as part of my Master’s at Imperial College London. Besides my academic interests, I’m also interested in EDI, sociology and psychology. I am also currently an MPLS EDI Fellow at the University of Oxford.

For my CV or any questions, feel free to reach out to me!