I am a fourth-year graduate student in the MIT Department of Mathematics, co-advised by Ankur Moitra and Jon Kelner. My interests lie broadly in theoretical computer science, machine learning, statistics, and optimization. More specifically, I currently work on algorithms and statistical lower bounds for structured inverse problems, such as community detection or estimating orientations in cryo-EM. One theme running through my research is to understand how algorithms and predictions from statistical physics (belief propagation and its variants) compare to those from convex optimization (semidefinite programming and the sum of squares hierarchy).

I spent my undergraduate years at Keble College, Oxford, mainly thinking about algebraic topology. Code for various topology computations is available on my github page.


Send emails to amelia at this domain, or to ameliaperry at mit.
My office at MIT is 2-390D. map