I’m a postdoctoral associate in Josh Tenenbaum’s Computational Cognitive Science Lab in the Department of Brain and Cognitive Sciences at MIT. Previously, I was a PhD student in Frank Wood’s group in the Department of Engineering Science at the University of Oxford. I’ve also interned at DeepMind, where I’ve worked with Yee Whye Teh.
I work on probabilistic programming, generative modeling and amortized inference. I have mainly looked at this through the lens of training deep neural networks to speed up sampling algorithms such as importance sampling and sequential Monte Carlo. Using these tools, I want to build systems that can efficiently learn concepts, understand scenes and agent behavior by drawing on research in computational cognitive science.