Deep Learning
Solving Inverse Problems via Diffusion Optimal Control Henry Li
We demonstrate that these limitations can be sidestepped by reframing the generative process as a discrete optimal control episode.
Scalable Early Childhood Reading Performance Prediction
Currently, students are identified as needing additional educational support using a'wait-to-fail' approach, i.e., waiting until a child has not made expected gains in reading before there is a reevaluation of their instructional needs.
Module-wise Training of Neural Networks via the Minimizing Movement Scheme Anonymous Author(s) Affiliation Address email
End-to-end backpropagation is the standard training method of neural networks.
Module-wise Training of Neural Networks via the Minimizing Movement Scheme
End-to-end backpropagation is the standard training method of neural networks.
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
We revisit this scenario as an experimental case study in Section 6.
FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning
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.
