logo
today local_bar
tensor programs

2 papers across 1 session

Poster Session 2

2 papers
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
#3903 Spotlight · Moritz Haas, Sebastian Bordt, Ulrike Luxburg, Leena Chennuru Vankadara
Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
#3503 · Mana Sakai, Ryo Karakida, Masaaki Imaizumi

We rigorously identify the infinite–width limit distribution of neurons within a single attention layer under realistic architectural dimensionality