Leonard Papenmeier
PhD Student
Bayesian Optimization, Gaussian Processes, Machine Learning, AutoML
CV.
Publications
| 2023 | Leonard Papenmeier, Luigi Nardi, Matthias Poloczek Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces Preprint. Accepted for publication at the NeurIPS 2023 (main conference). |
| 2023 | Erik Hellsten*, Carl Hvarfner*, Leonard Papenmeier*, Luigi Nardi High-dimensional Bayesian Optimization with Group Testing Preprint. * Equal contribution. |
| 2022 | Leonard Papenmeier, Luigi Nardi, Matthias Poloczek Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces Advances in Neural Information Processing Systems 35, NeurIPS 2022, New Orleans. |
| 2017 | Leonard Papenmeier (then: Hövelmann), Christoph M. Friedrich Fasttext and Gradient Boosted Trees at GermEval-2017 on Relevance Classification and Document-level Polarity GermEval Shared Task on Aspect-based Sentiment in Social Media Customer Feedback (GSCL), Hamburg, 2017. My Bachelor's thesis resulted in this submission. |
Education
| Since 09/2020 | PhD Student in Machine Learning at Lund University and Wallenberg AI, Autonomous Systems and Software Program, Sweden |
| 2019 | Exchange Semester (Data Science), NMBU, Ås, Norway |
| 2017-2020 | Master: Applied Computer Science, Ruhr-University, Bochum, Germany. Final grade: 95% (excellent) |
| 2013-2017 | Bachelor: Software Engineering, Dortmund University of Applied Sciences, Germany. Final grade: 1.6 (good) |
Work Experience
| 2018-2020 | Working student: Deep Learning and Computer Vision, img.ly GmbH, Bochum, Germany |
| 2016-2018 | Working student: Full-stack software development, adesso AG, Cologne, Germany |
| 2013-2016 | Apprenticeship: IT specialist, adesso AG & Chamber of Industry and Commerce (IHK), Germany |
Theses
| 2020 |
Leonard Papenmeier Semantic Representations in Variational Autoencoders as a Model of the Visual SystemMaster ThesisThis thesis was written at the Institute of Neural Computation at Ruhr-University Bochum, Germany and supervised by Laurenz Wiskott and Zahra Fayyaz. The goal was to investigate the role of semantic representations in the visual system. I investigated the hypothesis that variational autoencoders (VAEs) learn semantic representations of images by analyzing latent representations of VAEs trained on different datasets. We could not find strong evidence for this hypothesis.The thesis was graded with 100% (excellent). |
| 2017 |
Leonard Papenmeier (then: Hövelmann) Sentiment Analysis Based on Word Embeddings: Possible Improvements and Transfer to the German LanguageBachelor ThesisThis thesis was written at Dortmund University of Applied Sciences and Arts, Germany and supervised by Christoph M. Friedrich. I used (then very recent) word embeddings to improve sentiment on German text. I also participated in the GermEval Shared Task on Aspect-based Sentiment in Social Media Customer Feedback (GSCL) 2017 (see publications) and achieved the best result for the German language on one subtask and the second-best result on another subtask.The thesis was graded with 1.0 (very good). |
Programming Languages & Frameworks
PyTorch, BoTorch, Torch, Python, TensorFlow, Keras, Java, JavaScript, C, Scala, C++, Assembler (x86), HTML, CSS, PHP, Apache Spark, Spring Framework, Angular, UML, TypeScript, JPA, JSF, JSPScholarships
| 2017-2020 | Scholarship Program of the Friedrich-Ebert Foundation |
Leonard Papenmeier
PhD Student
Bayesian Optimization, Gaussian Processes, Machine Learning, AutoML