James Requeima is a postdoctoral fellow at the Vector Institute supervised by David Duvenaud. He completed a PhD in machine learning at the University of Cambridge in the Computational and Biological Learning Lab advised by Dr. Richard Turner. Before this, he completed a Master’s in machine learning, speech and language technology at the University of Cambridge advised by Dr. Zoubin Ghahramani FRS. In another life, James studied mathematics and his specialization was geometric group theory, combinatorial group theory, and algebraic topology. He completed a Master’s studying under Dani Wise FRS at McGill University and was a tenured member of the Department of Mathematics at Dawson College in Montréal.
- Neural Processes
- Deep Probabilistic Models
- Approximate Inference
- Autoregressive Conditional Neural Processes – ICLR 2023
- Practical Conditional Neural Processes Via Tractable Dependent Predictions – ICLR 2022
- Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes – NeurIPS 2019
- The Gaussian Process Autoregressive Regression Model (GPAR) – AISTATS 2019