Ulrich Schaechtle

Papers

Total Citations

H-Index

About

Ulrich Schaechtle is a researcher whose work sits at the intersection of probabilistic programming, machine learning, and statistical inference. His primary research focus is on making probabilistic programming languages more flexible and practical through the development of programmable inference systems. Schaechtle's most significant contribution is the introduction of "inference metaprogramming," a paradigm that allows users to customize inference algorithms within probabilistic programming languages rather than relying on rigid, black-box approaches. This work, detailed in his 2018 paper "Probabilistic programming with programmable inference," which has garnered 37 citations, represents a foundational step toward more adaptable and user-driven probabilistic computation. Additionally, his 2015 paper on "Probabilistic Programming with Gaussian Process Memoization" (5 citations) addresses the challenge of applying Gaussian Processes in complex domains like robotics and scientific computation. Through these contributions, Schaechtle has helped bridge the gap between theoretical probabilistic models and practical, real-world applications, offering tools that empower researchers and practitioners to tailor inference to their specific needs.