Nina Balcan

Nina Balcan is a Professor at Carnegie Mellon University and holds the Cadence Design Systems Professorship in Computer Science. She is affiliated with the School of Computer Science, specifically the Machine Learning Department (MLD) and Computer Science Department (CSD). Her research spans foundational aspects of machine learning, artificial intelligence, theoretical computer science, algorithmic game theory, and interdisciplinary connections in learning theory.

• Machine Learning
• Artificial Intelligence
• Theoretical Computer Science
• Algorithmic Game Theory
• Multi-Agent Systems
• Data-Driven Algorithm Design

Her recent work focuses on advancing algorithm design through machine learning, robustness in adversarial environments, and economic modeling. Key contributions include Learning to Branch (JACM 2024), Regret Minimization in Stackelberg Games (NeurIPS 2024), and Learning Accurate Decision Trees (UAI 2024, Outstanding Student Paper Award). She has pioneered novel approaches to data-driven optimization, semi-supervised learning, and privacy-preserving clustering.

Nina has received prestigious accolades including

• ACM Fellow
• AAAI Fellow
• Simons Investigator
• 2019 ACM Grace Murray Hopper Award

Her teaching at CMU includes graduate courses on machine learning, advanced machine learning, and specialized topics like algorithmic game theory.