Statistical Learning
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
While existing defenses often rely on regularization techniques to reduce information leakage, they remain vulnerable to recent attacks.
Double and Single Descent in Causal Inference with an Application to High-Dimensional Synthetic Control
Motivated by a recent literature on the double-descent phenomenon in machine learning, we consider highly over-parameterized models in causal inference, including synthetic control with many control units.
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training Yefan Zhou
However, such a global learning rate schedule does not take into account the structural characteristics of neural networks (NNs).
Mixture of Demonstrations for In-Context Learning Song Wang
We further design an expert-wise training strategy to alleviate the impact of unhelpful demonstrations when optimizing the retriever model.
