Explainable and Fair Machine Learning Algorithms with Applications in Biomedical Data Science

Recent advances in machine learning have spawned innovation and prosperity in various fields. In machine learning models, nonlinearity facilitates more flexibility and ability to better fit the data. However, the improved model flexibility is often accompanied by challenges such as overfitting, less interpretability, and bias.

Thus, my research has been focusing on designing new feasible nonlinear machine learning models to address the above different challenges, and bringing discoveries in both theory and applications. In this talk, I will first introduce our explainable models for regression and classification. We derive the model convergence rate under mild conditions in the hypothesis space, and uncover new potential biomarkers in Alzheimer's disease study.

Second, I will introduce our deep generative adversarial network to analyze the temporal correlation structure in longitudinal data, and improve prediction accuracy in Alzheimer's early diagnosis. Last but not least, I will introduce a new framework to improve the interpretability and fairness of deep learning models.