Suche
News
You are here
M.Sc. Jovita Lukasik
Room:
external PhD student
E-Mail:
Address:
Universität Siegen
Lehrstuhl für Visual Computing
Hölderlinstraße 3
57076 Siegen
My work is funded by the BMBF (Federal Ministry of Education and Research) in the project DeToL – Deep Topology Learning at the University of Mannheim. I am also affiliated with MPII.
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.
Publications
S. Jung, J. Lukasik, M. Keuper, Neural Architecture Design and Robustness: A Dataset, accepted to ICLR 2023.
J. Lukasik, S. Jung, M. Keuper, Learning Where to Look -- Generative NAS is Surprisingly Efficient, accepted to ECCV 2022.
J. Siems, L. Zimmer, A. Zela, J. Lukasik, M. Keuper and F. Hutter, NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search, ICLR, 2022.
J. Lukasik, S. Jung, M. Keuper, Learning Where to Look -- Generative NAS is Surprisingly Efficient, accepted to ECCV 2022.
J. Siems, L. Zimmer, A. Zela, J. Lukasik, M. Keuper and F. Hutter, NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search, ICLR, 2022.
J. Geiping, J. Lukasik, M. Keuper, M. Moeller, DARTS for Inverse Problems: a Study on Sensitivity, NeurIPS workshop on Inverse Problems, 2021.
J. Lukasik, D. Friede, A. Zela, F. Hutter, M. Keuper, Smooth variational graph embeddings for efficient neural architecture search, IJCNN 2021.
J. Lukasik, M. Keuper, M. Singh, J. Yarkony, A Benders Decomposition Approach to Correlation Clustering, 2020 IEEE/ACM Workshop on Machine Learning in High Performance Computing at SC20.
J. Lukasik, D. Friede, H. Stuckenschmidt, M. Keuper, Neural Architecture Performance Prediction Using Graph Neural Networks, DAGM German Conference on Pattern Recognition, 188-201, 2020.