I am a PhD candidate in computer science at the University of Toronto, supervised by Sasho Nikolov and Toni Pitassi. My present research focuses on differential privacy, particularly algorithms in the local model and lower bounds against it.
Recent work, with Sasho Nikolov and
‘The Power of Factorization Mechanisms in Local
and Central Differential Privacy’
gave general characterizations of the sample complexity
for answering linear queries - and agnostic PAC learning -
in the local and central models of privacy.
My Master’s was supervised by Dan Roy, with whom I studied models of computationally-efficient samplability.
My undergrad was in the Mathematics Specialist program at the University of Toronto, with a dose of humanities on the side.
Alexander Edmonds, Concepts of Efficient Samplability. MSc Thesis. [thesis]