Co-occurring keywords · papers mentioning both
Papers
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
ICML 2025
Adaptive Proximal Gradient Method for Convex Optimization
NeurIPS 2024
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
ICML 2021
SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization
ICML 2016
Intrinsic Characterization of Dynamic Surfaces
CVPR 2013