Goto

Collaborating Authors

 training dataset






Non-asymptotic Convergence of Training Transformers for Next-token Prediction

Neural Information Processing Systems

NTP is limited, with existing studies focusing mainly on asymptotic performance. This paper provides a fine-grained non-asymptotic analysis of the training dynamics of a one-layer transformer consisting of a self-attention module followed by a feed-forward layer.





FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

Neural Information Processing Systems

To bridge this gap, we model the strategic interactions between the defender and dynamic attackers as a minimax game. Based on the analysis of the game, we design an interactive defense mechanism FedGame. We prove that under mild assumptions, the global model trained with FedGame under backdoor attacks is close to that trained without attacks.