University of Oxford
Andrew Wiles Building
Radcliffe Observatory Quarter
I am interested in the mathematical analysis of algorithms used for machine learning, and more generally information inference from data. In the problems I typically work on I assume that the data possesses some structure, for example sparse under a certain transform, arising as a result of a particular generative model or lying on some smooth manifold, and then try to analyse existing algorithms, or derive new ones, using this context. To do this I leverage tools, techniques and ideas from a number of areas, including applied probability, numerical linear algebra, optimization and discrete mathematics. I am currently particularly interested in understanding how and why deep neural networks work as well as they do.
I am also a student at the Turing Institute, the UK's National Centre for AI and Data Science.