B.S. Engineering Physics (Summa Cum Laude),
Cornell University, 2010
M.S. Applied Physics, Stanford University, 2013
Ph.D. Applied Physics, Stanford University, 2016
My broad research interest is in applying statistical physics to understand phenomena in other fields such as neuroscience, machine learning, and biology. I did my PhD research with Surya Ganguli as a member of the Neural Dynamics and Computation Lab at Stanford University and focused on the emerging field of high dimensional statistics, where inference accuracy is hindered by a high dimensional parameter space (the curse of dimensionality). To analyze inference algorithms, I exploit the analogy between disordered systems optimizing an energy function and inference algorithms optimizing parameters estimates, where the data serves as fixed or quenched disorder in the system. By applying analytic techniques originally used by statistical physicists to understand large, randomly interacting spin systems, one can derive relationships between accuracy and dimensionality for inference algorithms in the big data regime and derive more effective algorithms.