François-Xavier Bristol on Model Misspecification in Scientific Modeling and how to Navigate them

In this episode we welcome François-Xavier Briol, an Associate Professor in Statistical Science at UCL, focuses on computational statistics and machine learning methodology. At UCL, he supervises PhD students in developing new approaches for large-scale models in biological, physical, and engineering sciences. He also contributes to the UCL AI Centre and leads research at The Alan Turing Institute, exploring statistical machine learning fundamentals. Previously, François-Xavier worked as a Research Associate at the University of Cambridge and Imperial College London, focusing on multimodal data analysis projects. He holds a PhD in Statistics from the University of Warwick and has received recognition for his dissertation on ‘Statistical Computation with Kernels’. François-Xavier is committed to advancing statistical science through innovative research and impactful teaching at UCL.

Together with FX we delve into the nuances of model misspecification and its implications in scientific modeling, emphasizing the adage that “all models are wrong, but some are useful.” FX shares insights on personal growth and highlights the pivotal role of collaboration in his academic journey.