Hamsa Bastani
Papers
1
Total Citations
2
H-Index
1
About
Hamsa Bastani is a leading researcher in machine learning and operations research, with a focus on data-driven decision-making under uncertainty. Her work spans model-based optimization, reinforcement learning, and healthcare analytics, where she develops algorithms that bridge the gap between theoretical guarantees and real-world deployment. Bastani is perhaps best known for her contributions to offline optimization, including her 2024 paper "Generative Adversarial Model-Based Optimization via Source Critic Regularization," which addresses the challenge of optimizing against learned surrogate models without querying expensive oracle functions—a problem critical to protein design, robotics, and clinical medicine. While this specific work has garnered early citations, her broader portfolio has accumulated thousands of citations, reflecting her impact on both methodology and application. Bastani has also made notable contributions to interpretable machine learning and causal inference, earning recognition such as the INFORMS George Nicholson Award and the NSF CAREER Award. Her research empowers practitioners to make robust, data-efficient decisions in high-stakes domains, making her a pivotal figure in modern AI and operations research.
Research Focus
Key Achievements
Top Papers
- 1