David S. Matheson

Papers

Total Citations

629

H-Index

About

David S. Matheson is a leading researcher in machine learning, with a primary focus on Bayesian optimization and its application to high-dimensional problems. His most significant contribution is the development of random embedding techniques that break the traditional dimensionality barrier in Bayesian optimization. In his seminal 2013 paper, "Bayesian optimization in high dimensions via random embeddings" (242 citations), he introduced a method to efficiently optimize functions in high-dimensional spaces by projecting them into lower-dimensional subspaces. This work was extended in his highly influential 2016 paper, "Bayesian Optimization in a Billion Dimensions via Random Embeddings" (372 citations), which demonstrated that Bayesian optimization could be scaled to problems with billions of dimensions—a feat previously considered impossible. Matheson's research has enabled practical applications in robotics, sensor placement, advertising, and automatic algorithm configuration, where high-dimensional optimization is critical. His work is widely recognized for its theoretical elegance and practical impact, making him a key figure in advancing the frontiers of Bayesian optimization and its real-world deployment.