Jessica Sorrell

Jessica Sorrell is an Assistant Professor in the Department of Computer Science at Johns Hopkins University and a member of the Data Science and AI Institute. Her research focuses on the theoretical foundations of machine learning, emphasizing replicability, privacy, fairness, and robustness. She has contributed to lattice-based cryptography and secure computation.

• Johns Hopkins University (Assistant Professor, Department of Computer Science)
• University of Pennsylvania (Postdoctoral Researcher)
• University of California, San Diego (PhD in Computer Science)
• Rochester Institute of Technology (Undergraduate in Applied Mathematics)

Research Areas:

• Theoretical machine learning
• Replicability and reproducibility of statistical algorithms
• Differential privacy and adaptive generalization
• Lattice-based cryptography
• Secure computation protocols

Publications highlight her work on replicable reinforcement learning, algorithmic stability, and cryptographic techniques. She previously studied at UCSD under Daniele Micciancio and Russell Impagliazzo.

Teaching: Spring 2025: Theory of Replicable Machine Learning (EN.601.774).