Greg Anderson

Greg Anderson is an Assistant Professor of Computer Science at Reed College, affiliated with the Division of Mathematical and Natural Sciences. His research focuses on the intersection of programming languages and machine learning, emphasizing safety and robustness in deep learning systems. He holds a B.S. in Computer Engineering and Mathematics from the University of Virginia and a Ph.D. in Computer Science from the University of Texas at Austin, advised by Isil Dillig and Swarat Chaudhuri.

Anderson's research explores neurosymbolic learning, combining neural networks with structured programs, and developing frameworks for formally guaranteed safety in reinforcement learning systems. His work includes robustness verification of neural networks (PLDI'19) and safety-critical exploration strategies (ICLR'23). He also investigates machine learning applications in program analysis and synthesis, such as predicate learning for synthesis tools (CAV'18).

Teaching includes foundational computer science courses (CSCI 121/221), advanced topics like deep learning (CSCI 378), programming languages (CSCI 384), and computer systems (CSCI 389). His 2019 PLDI paper received a Distinguished Paper Award for its synergistic approach to neural network robustness analysis.

Anderson’s research bridges formal methods with machine learning, addressing critical challenges in system safety through verification, abstraction techniques, and neurosymbolic integration. His work emphasizes practical tools for ensuring reliability in AI systems.