Skip to content
conftrace_

learning rate scheduler

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

stochastic gradient descent (2) supernet training (1) client aggregation (1) convergence theory (1) model expansion (1) multi-task optimization (1) gradient difference (1) large language model (1) normalized gradient descent (1) dynamic training strategy (1)

Papers

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search CVPR 2025 Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025 AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop UAI 2024 FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent ICLR 2024 Hop, skip, jump to Convergence: Dynamics of Learning Rate Transitions for Improved Training of Large Language Models EMNLP 2024 LEMON: Lossless model expansion ICLR 2024 Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets AISTATS 2023