Raul Astudillo Marban
Assistant Professor of Machine Learning
Research Interests
Professor Astudillo’s research focuses on developing principled algorithms for data-efficient learning and decision-making in complex, uncertain environments. His work integrates machine learning, optimization, and generative models to guide adaptive experimentation and data acquisition, enabling breakthroughs in personalized healthcare, engineering design, and scientific discovery.
Prior to joining MBZUAI, Professor Astudillo was a Postdoctoral Scholar in the Department of Computing and Mathematical Sciences at the California Institute of Technology, where he worked with Professor Yisong Yue. He earned his Ph.D. in Operations Research and Information Engineering from Cornell University, under the supervision of Professor Peter Frazier. During his doctoral studies, he also held a Visiting Researcher position at Meta. He holds a B.Sc. in Mathematics from the University of Guanajuato and the Center for Research in Mathematics in Mexico.
Professor Astudillo’s research focuses on developing principled algorithms for data-efficient learning and decision-making in complex, uncertain environments. His work lies at the intersection of machine learning, optimization, and generative modeling, with applications in adaptive experimentation, data acquisition, and automated discovery. These methods have advanced solutions in personalized healthcare, engineering design, and scientific research.
He has been recognized as a Rising Star in Management Science and Engineering by Stanford University, and as a Rising Star in Data Science by both the University of Chicago and UC San Diego. His research has earned multiple accolades, including Best Paper Finalist honors at INFORMS and the prestigious Computing, Data, and Society Postdoctoral Fellowship from Caltech.
- Postdoctoral Fellowship Computing, Data, and Society by the California Institute of Technology
- Visiting Resercher, Meta
- Ph.D. in Operations Research and Information Engineering from Cornell University
- M.S. in Computer Science from the University of North Carolina at Chapel Hill
- Rising Star in Data Science, University of Chicago and UC San Diego, 2024. Rising Star in Management Science & Engineering, Stanford University, 2024.
- Finalist, INFORMS Data Mining Best Paper Competition, 2024.
- Finalist, INFORMS Undergraduate Operations Research Prize Competition (Mentee), 2024.
- Computing, Data, and Society Postdoctoral Fellowship, California Institute of Technology, 2024–2025.
- Spotlight Presentation, ICML Workshop on Adaptive Experimental Design, 2022.
Recent Publications:
- J. Yang, W. Chu, D. Khalil, R. Astudillo, F. Arnold, and Y. Yue, “Steering generative models with experimental data for protein fitness optimization,” ICLR Workshop on Generative and Experimental Perspectives for Biomolecular Design, 2025.
- J. Yang, R. Lal, J. Bowden, R. Astudillo, M. Hameedi, Y. Yue, and F. Arnold, “Active learning-assisted directed evolution,” Nature Communications, 2025.
- C. Cheng, R. Astudillo, T. Desautels, and Y. Yue, “Practical Bayesian algorithm execution via posterior sampling,” NeurIPS, 2024. (Finalist, INFORMS Undergraduate Operations Research Prize Competition) Q. Xie, R. Astudillo, P. Frazier, Z. Scully, and A. Terein, “Cost-aware Bayesian optimization via the Pandora’s box Gittins index,” NeurIPS, 2024. (Finalist, INFORMS Data Mining Best Paper Competition)
- R. Astudillo, Z. Lin, E. Bakshy, and P. Frazier, “qEUBO: A decision-theoretic acquisition function for preferential Bayesian optimization,” AISTATS, 2023. R. Astudillo and P. Frazier, “Bayesian optimization of function networks,” NeurIPS, 2021.