"parameterization methods" Papers
3 papers found
Compute Better Spent: Replacing Dense Layers with Structured Matrices
Shikai Qiu, Andres Potapczynski, Marc Finzi et al.
ICML 2024poster
Non-Vacuous Generalization Bounds for Large Language Models
Sanae Lotfi, Marc Finzi, Yilun Kuang et al.
ICML 2024poster
Scaling Exponents Across Parameterizations and Optimizers
Katie Everett, Lechao Xiao, Mitchell Wortsman et al.
ICML 2024poster