My research interests are broadly in theoretical machine learning and statistics. My current focus is on the theory of deep learning. More specifically, I am interested in: (1) provable guarantees for optimization and generalization in neural networks and (2) principled explanations for phenomena that arise when training deep networks in practice. In the past, I’ve conducted research in areas such as causal structure learning and applied probability. Check out my publications page for more!
I previously received my B.S. degrees in Math and Computer Science (2020) and my M.Eng degree in EECS (2021) from MIT, where I was advised by Caroline Uhler. I am supported by the DoD NDSEG Fellowship.
You can contact me at eshnich (at) princeton (dot) edu.