Can AI surrogates outperform their training data? Turns out the answer is yes - with a few caveats 😉 https://tum-pbs.github.io/emulator-superiority/ I'm happy to higlight Felix' #NeurIPS paper to be presented next week in San Diego. He discovered this "superiority", and developed a theory to analyze when it does show up. This surprising behavior leads to interesting and fundamental questions about the role of training data, and about how neural networks and learning-based surrogates should be evaluated.