{"id":20053,"date":"2026-02-14T13:58:44","date_gmt":"2026-02-14T12:58:44","guid":{"rendered":"https:\/\/wi.bwl.uni-mainz.de\/?page_id=20053"},"modified":"2026-09-12T13:52:23","modified_gmt":"2026-09-12T11:52:23","slug":"philipp-anthes","status":"publish","type":"page","link":"https:\/\/wi.bwl.uni-mainz.de\/en\/philipp-anthes\/","title":{"rendered":"Philipp Anthes"},"content":{"rendered":"<\/jgu-base-heading>\n\n\n\n
\n
\n \n<\/jgu-base-image>\n\n\n \n\n \n<\/jgu-base-listitem>\n\n\n \n<\/jgu-base-listitem>\n\n\n \n<\/jgu-base-listitem>\n\n<\/jgu-base-contactcard>\n\n\n

<\/p>\n<\/div>\n\n\n\n

<\/div>\n\n\n\n
\n \n\n \n\n

Philipp Anthes (M.Sc.) has been a doctoral candidate at the chair since 2023, working at the intersection of machine learning and evolutionary learning. He completed his B.Sc. in Economics from 2017 to 2020 and his M.Sc. in Management from 2020 to 2023.<\/p>\n\n\n\n

<\/p>\n\n\n\n

\n

<\/p>\n<\/blockquote>\n\n\n<\/jgu-base-tabsitem>\n\n\n \n\n

His research centers on genetic programming (GP), in particular on how generative transformer models can be integrated into evolutionary search as variation operators. The aim is to vary solutions in the semantic rather than the syntactic space, yielding compact and accurate models for symbolic regression problems. The underlying approach (Transformer Semantic Genetic Programming<\/em>, TSGP) received the Best Paper Award at GECCO 2025.
<\/p>\n\n\n<\/jgu-base-tabsitem>\n\n\n \n\n \n<\/jgu-base-buttonitem>\n\n<\/jgu-base-button>\n\n\n

<\/p>\n\n\n\n \n<\/jgu-base-fis>\n\n<\/jgu-base-tabsitem>\n\n\n \n\n

I currently supervise the following courses:<\/p>\n\n\n\n