From Quantum Entanglement to Future Data-Driven Engineering - Rothschild Lecture

Explore a comprehensive lecture on the intersection of data science, machine learning, and high-dimensional Bayesian statistics in engineering applications. Delve into the growing contributions from numerical analysis and scientific computing to efficiently combine data and physical models for better understanding and control of engineering problems. Examine the challenges, opportunities, and potential contributions in this field. Discover two exemplary approaches using surrogates to accelerate Bayesian computation in high-dimensional PDE-constrained applications: multilevel delayed acceptance MCMC and a measure-transport approach based on low-rank tensor approximations. Gain insights into the mathematical and statistical foundations of future data-driven engineering through this Rothschild Lecture delivered by Professor Robert Scheichl from Ruprecht-Karls-Universität Heidelberg at the Isaac Newton Institute for Mathematical Sciences.