Postdoctoral Scholar in Machine Learning Foundations
The University of Chicago is seeking candidates for postdoctoral research on machine learning foundations. Postdoctoral scholars will lead interdisciplinary research projects and collaborations in machine learning methods that incorporate physical models and constraints, providing additional robustness and reduced sample complexity. Scholars will create new methods that draw upon methods and insights from multiple fields, including inverse problems, data assimilation, optimization, and statistics, and explore applications in climate science, biomedical imaging, and remote sensing. In addition to competitive salary and benefits, the fellowship also includes funding for independent travel to workshops, conferences, and other universities and research labs. Interested applicants should contact Rebecca Willett with a CV, research statement, and letter of reference.
Machine-Learning Accelerated Simulations for Forecasting, Data Assimilation, and Extreme Events
We seek postdoctoral scholars to develop and investigate ML-based surrogate models for representing differential equations, solving inverse problems, and performing data assimilation tasks that may surmount the limitations of current methods. Our focus is on high-dimensional settings, generalization across a range of parameters and initial and boundary conditions, and accuracy in the presence of rare, extreme events. Success will require synergistic advances in foundational ML, applied mathematics, optimization, and statistics. Our interdisciplinary team includes researchers from applied math, statistics, computer science, and mathematics at the University of Chicago and Argonne National Laboratory. Interested applicants should contact Rebecca Willett with a CV, research statement, and letter of reference.