Scaling Exponents Across Parameterizations and Optimizers.
Katie EverettLechao XiaoMitchell WortsmanAlexander A. AlemiRoman NovakPeter J. LiuIzzeddin GurJascha Sohl-DicksteinLeslie Pack KaelblingJaehoon LeeJeffrey PenningtonPublished in: CoRR (2024)