Private Convex

Private convex optimization focuses on developing algorithms that solve convex optimization problems while preserving the privacy of the data used to define the problem. Current research emphasizes efficient algorithms for various settings, including differentially private stochastic gradient descent (DP-SGD) and zeroth-order methods, and explores their application in areas like federated learning and matrix approximation, often employing techniques like the exponential mechanism and loss approximation. This field is crucial for enabling the use of sensitive data in machine learning and other applications while adhering to strong privacy guarantees, impacting both theoretical understanding of privacy-preserving computation and the development of practical privacy-enhancing technologies.