Co-occurring keywords · papers mentioning both
Papers
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
ICLR 2025
Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network
ICML 2024
Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions
ICML 2023
Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks
NeurIPS 2020