3 papers
cs.LG2024
Incorporating Domain Differential Equations into Graph Convolutional Networks to Lower Generalization Discrepancy
Yue Sun, Chao Chen, Yuesheng Xu +3
Ensuring both accuracy and robustness in time series prediction is critical to many applications, ranging from urban planning to pandemic management. With sufficient training data…
cs.LG2024
Robust Conformal Prediction under Distribution Shift via Physics-Informed Structural Causal Model
Rui Xu, Yue Sun, Chao Chen +2
Uncertainty is critical to reliable decision-making with machine learning. Conformal prediction (CP) handles uncertainty by predicting a set on a test input, hoping the set to cove…
cs.LG2024
RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
Ce Feng, Parv Venkitasubramaniam
The rise of IoT devices has prompted the demand for deploying machine learning at-the-edge with real-time, efficient, and secure data processing. In this context, implementing mach…