Adam Gaier

Papers

Total Citations

H-Index

About

Adam Gaier is a leading researcher in evolutionary computation and design optimization, whose work centers on developing algorithms that enable machines to creatively explore complex design spaces. His major contributions lie at the intersection of surrogate modeling and illumination algorithms, most notably through his invention of Surrogate-Assisted Illumination (SAIL). This method, detailed in his highly cited 2017 paper (25 citations), revolutionized aerodynamic design by allowing for the generation of diverse, high-performing design repertoires—a concept borrowed from robotics for damage recovery—rather than a single optimal solution. Gaier further advanced the field by automating the discovery of efficient data representations, combining MAP-Elites with Variational Autoencoders (2020, 6 citations) to learn encodings that capture the essence of top solutions. His work on predicting neural network performance through phenotypic modeling (2019, 7 citations) also reduced the computational burden of expensive objective functions. Through these innovations, Gaier has established himself as a key figure in making evolutionary algorithms more practical and powerful for real-world engineering challenges.