Skip to main content

Please join us for a Statistics and DSI joint colloquium.

Monday, February 17
11:30am – 12:30pm
Jones Hall 303
5747 S Ellis Avenue
Chicago, IL 60637

Abstract: Deep learning’s success stems from the ability of neural networks to automatically discover meaningful representations from raw data. In this talk, I will describe some recent insights into how optimization enables this learning process. First, I will show how optimization algorithms exhibit surprisingly rich dynamics when training neural networks, and how these complex dynamics are actually crucial to their success – enabling them to find solutions that generalize well, navigate challenging loss landscapes, and efficiently adapt to local curvature. I will then explore how optimization enables neural networks to adapt to low-dimensional structure in the data, how the geometry of the loss landscape shapes the difficulty of feature learning, and how these ideas extend to in-context learning in transformers.

Bio:  Alex Damian: I am a fifth year Ph.D. student in Applied and Computational Mathematics at Princeton University and I am fortunate to be advised by Prof. Jason Lee. I’m intersted in deep learning theory, especially optimization and representation learning. My research is supported by a National Science Foundation Graduate Research Fellowship and a Jane Street Graduate Research Fellowship.

I did my undergrad at Duke University where I received a B.S. in Mathematics and was fortunate to work with Prof. Cynthia Rudin and Prof. Hau-Tieng Wu.

arrow-left-smallarrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-long-yellowarrow-right-smallclosefacet-arrow-down-whitefacet-arrow-downCheckedCheckedlink-outmag-glass