4 papers
AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction
Ziqiang Cui, Han Shi, Bowei He +8
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several f…
Understanding Generalization of Federated Learning: the Trade-off between Model Stability and Optimization
Dun Zeng, Zheshun Wu, Shiyu Liu +3
Federated Learning (FL) is a distributed learning approach that trains machine learning models across multiple devices while keeping their local data private. However, FL often fac…
IDInit: A Universal and Stable Initialization Method for Neural Network Training
Yu Pan, Chaozheng Wang, Zekai Wu +3
Deep neural networks have achieved remarkable accomplishments in practice. The success of these networks hinges on effective initialization methods, which are vital for ensuring st…
On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond
Dun Zeng, Zenglin Xu, Shiyu Liu +3
Federated averaging (FedAvg) is the most fundamental algorithm in Federated learning (FL). Previous theoretical results assert that FedAvg convergence and generalization degenerate…