ISyE Foundations of Private Optimization for Modern Machine Learning
2188 Mechanical Engineering Building 1513 University Avenue, Madison, WI, United StatesHow 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...