Jovita Lukasik

Researcher

University of Mannheim
B6, 26, Room B 003
D-68159 Mannheim

Email: jovita (at) informatik.uni-mannheim.de

I am a Ph.D. candidate in the focus group of Computer Vision in the Data and Web Science Group and in the computer vision and machine learning group at the Max-Planck-Institute for Informatics. I am supervised by Prof. Dr.-Ing. Margret Keuper. 

I was part of the organization team of the second NAS workshop @ ICLR 2021 and I am co-organizing a series of virtual seminars on AutoML.

Please also see: https://jovitalukasik.github.io/

• 2019-present, Ph.D. student, Computer Science, University of Mannheim
• 2016–2019, M.Sc., Mathematics in Business and Economics, University of Mannheim
• 2012- 2015, B.Sc., Mathematical Finance, University of Konstanz

• Lukasik, J. ,Jung, S., Keuper, M.,:  Learning Where To Look – Generative NAS is Surprisingly Efficient. European Conference on Computer Vision (2022)
• Zela, A., Siems, J., Zimmer, J., Lukasik, J., Keuper, M., Hutter, F.: Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks. International Conference on Learning Representations (2022)
• Geiping,J., Lukasik, J., Keuper, M., Moeller, M.: DARTS for Inverse Problems: a Study on Stability. NeurIPS 2021 Deep Inverse Workshop (2021)
• Lukasik, J., Friede, D., Zela, A., Hutter, F., Keuper M.:
  Smooth Variational Graph Embeddings for Efficient Neural Architecture Search.  IJCNN(2021)
• Lukasik, J., Friede, D., Stuckenschmidt, H., Keuper, M.,: Neural Architecture Performance Prediction Using Graph Neural Networks. GCPR 2020, 188–201
• Lukasik, J., Keuper, M., Singh, M,. Yarkony, J.: A Benders Decomposition Approach to Correlation Clustering. Workshop  on Machine Learning in HPC Environments in SC20