Loading Events

« All Events

  • This event has passed.

IDEAS/STAT Optimization Seminar: “Foundations of Deep Learning: Optimization and Representation Learning”

February 13 at 12:00 PM - 1:15 PM

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.

 

Zoom link: https://upenn.zoom.us/j/93151261686 (Meeting ID: 931 5126 1686)

Alexandru Damian

Ph.D. student, Applied and Computational Mathematics (PACM) at Princeton University

Alex Damian is a fifth-year Ph.D. student in the Program for Applied and Computational Mathematics (PACM) at Princeton University, advised by Jason Lee. His research is focused on deep learning theory with an emphasis on optimization and representation learning. His work has been supported by an NSF Graduate Research Fellowship and a Jane Street Graduate Research Fellowship.

Details

Date:
February 13
Time:
12:00 PM - 1:15 PM
Event Categories:
,
Event Tags:
, , ,
Website:
https://jasonaltschuler.github.io/opt-seminar/

Organizer

IDEAS Center
View Organizer Website

Venue

Amy Gutmann Hall, Room 414
3333 Chestnut Street
Philadelphia, 19104 United States
+ Google Map