Projects and Publications.

Under construction, more coming soon...

Self-Adaptive Visual Navigation

In humans there is no explicit distinction between training and inference — we learn as we perform. We present a meta-reinforcement learning solution for visual navigation, where an agent learns via self-supervised interaction as it navigates novel environments. (paper)

Interacting Particle Systems and Efficient Approximations for Large Sparse Graphs

In my honors thesis, I examined stochastic dynamics on networks under the supervision of Professor Kavita Ramanan. We used symmetries which may arise in sparse networks to develop efficient approximations. (paper — sorry this takes a while to load, zipped_paper, slides)

Various Class Projects

For coding theory I learned about variational autoencoders. For computer vision I learned about style transfer. For intro to data science I visualized trends in neuroscience literature. For computational linear algebra I studied PageRank. For distributed systems I implemented a distributed file system.

About me.

I'm a Predoctoral Young Investigator at the Allen Institute for Artificial Intelligence. I am from Toronto, Ontario and completed my undergraduate degree in Applied Mathematics - Computer Science at Brown University in 2018.

Please click here for my resume.

My research interests include machine learning, computer vision, graphical models, meta-learning, and probability theory. In the past few years I've been lucky enough to work with some increadibly smart people on some very interesting problems (see here!).

I am additionally very passionate about music, hiking, teaching, and reading.