Generalization in Attention-Based Models: Insights from Solvable High-Dimensional Models
Lenka Zdeborová
Location:
SEC
150 Western Avenue, Allston, MA, United States
Room: LL2.221
Lenka Zdeborová
Stella Biderman
Judith Ellen Fan
Azalia Mirhoseini
Danqi Chen
Tatiana Engel