3 papers
cs.LG2025
Layer-wise Adaptive Gradient Norm Penalizing Method for Efficient and Accurate Deep Learning
Sunwoo Lee
Sharpness-aware minimization (SAM) is known to improve the generalization performance of neural networks. However, it is not widely used in real-world applications yet due to its e…
cs.LG2025
Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning
Junhyuk Jo, Jihyun Lim, Sunwoo Lee
Sharpness-Aware Minimization (SAM) is an optimization method that improves generalization performance of machine learning models. Despite its superior generalization, SAM has not b…
cs.LG2025
Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogeneous Federated Learning
Jihyun Lim, Junhyuk Jo, Tuo Zhang +1
Online Knowledge Distillation (KD) is recently highlighted to train large models in Federated Learning (FL) environments. Many existing studies adopt the logit ensemble method to p…