How can we develop optimization algorithms for training machine learning models that preserve the privacy of individuals' training data? In this talk, I will present my work addressing this challenge through differential privacy (DP). Differential privacy offers a rigorous, quantifiable standard of privacy that limits potential leakage of training data. I will explore the fundamental...

Artificial intelligence (AI) technologies are increasingly integrated into our lives, enabling a new paradigm of human-AI decision-making where AI provides recommendations, and humans make the final decision. However, such human-AI...