2024 Poster "second-order optimization" Papers
4 papers found
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
Wu Lin, Felix Dangel, Runa Eschenhagen et al.
ICML 2024posterarXiv:2402.03496
Error Feedback Can Accurately Compress Preconditioners
Ionut-Vlad Modoranu, Aleksei Kalinov, Eldar Kurtic et al.
ICML 2024posterarXiv:2306.06098
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
Mohamed Elsayed, Homayoon Farrahi, Felix Dangel et al.
ICML 2024posterarXiv:2406.03276
Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC
Wu Lin, Felix Dangel, Runa Eschenhagen et al.
ICML 2024poster