Hi! I'm a researcher at Microsoft Research NYC. (We're hiring!) My work weaves between the theory, empirical science, and pragmatic design of learning algorithms. In an immediate research capacity, I care about:
In other capacities, I care about fairness, alignment, intersectionality, and boundary objects.
Bringing these together, I'm currently particularly obsessed with planning, reasoning, and abstraction in deep sequence models. I'd like to see these done more directly, reliably, and efficiently. With a superb set of collaborators, I've been building out mental models for how to learn the right circuits in today's non-convex and non-stochastic world.
I completed my Ph.D. in Computer Science at Princeton, under the supervision of Prof. Elad Hazan, where we worked on convexifying non-convex problems in filtering and control. For the latter half of that wonderful adventure, I was a student researcher at Google AI, where we worked on the theory and design of large-scale optimizers. Before that, I completed a B.S. in Computer Science at Yale, and grew up in Toronto.