Cite
Notes
Only stored in your browser.
Attribution
Don't be lazy: CompleteP enables compute-efficient deep transformers
arXiv 2025
Dynamically Learning to Integrate in Recurrent Neural Networks
Learning Curves for SGD on Structured Features
learning-curves-for-sgd-on-structured-1
from 3 papers
Cengiz Pehlevan
Bin Claire Zhang
Boris Hanin
Jacob A. Zavatone-Veth
Joel Hestness
Jordan Cotler
Lorenzo Noci
Mufan Li
Nolan Dey
Shane Bergsma