I am a PhD student on the Cambridge-Tübingen programme, jointly supervised by Carl Rasmussen and Bernhard Schölkopf.
Earlier in my PhD I worked primarily in causality, but recently have shifted my interests towards generative modelling, in particular Wasserstein Auto-Encoders. My ambition is to connect the success of learned representations (deep learning) with foundational work on causal inference.
Before starting my PhD, I studied for a masters in Computational Statistics and Machine Learning at UCL / Gatsby Unit where I was supervised by Arthur Gretton.
Personal homepage: http://paulrubenstein.co.uk/
Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence (UAI), (Editors: Gal Elidan, Kristian Kersting, and Alexander T. Ihler), Association for Uncertainty in Artificial Intelligence (AUAI), Conference on Uncertainty in Artificial Intelligence (UAI), August 2017, *equal contribution (conference)
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems