Computer and Information Science
Jacob Gardner works at the intersection of machine learning, artificial intelligence and scientific discovery. His research focuses on probabilistic machine learning, a branch of AI that helps computers make decisions while accounting for uncertainty. In practice, this means building tools that can help scientists search through enormous design spaces — such as possible antibiotics, vaccines, antibodies, materials or therapeutic molecules — more efficiently than trial and error alone.
A major focus of Gardner’s work is Bayesian optimization, a machine learning approach for deciding which experiment, design or candidate solution to try next when testing is expensive or time-consuming. Recent publications from his group explore how to make these methods more scalable, reliable and useful for high-dimensional problems such as molecular design, protein design, robotics and clinical medicine. His work also includes broader applications of AI, including models that learn performance-improving code edits and methods that make optimization more effective when data or computational resources are limited.
Through this research, Gardner aims to create AI systems that can accelerate discovery across biology, chemistry, medicine and other scientific fields. One long-term goal is to help make “self-driving labs” possible: systems where AI proposes new molecules or materials, automated tools test them, and the results are fed back into the model so it can improve its next suggestions. Gardner’s work shows how computer science can move beyond screens and software to shape real-world advances in health, science and technology.