DI (FH) Michael Roßbory

Researcher Data Analysis Systems
Telefon: +43 50 343 860


Data Science - DAS

M. Kumar, M. Roßbory, B. Moser, B. Freudenthaler. An optimal (∊,δ)-differentially private learning of distributed deep fuzzy model. Information Services, volume online first, DOI: 10.1016/j.ins.2020.07.044, August, 2020.

M. Kumar, M. Roßbory, B. Moser, B. Freudenthaler. Differentially private learning of distributed deep models. MAP '20 Adjunct: Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization, pages 193-200, DOI 10.1145/3386392.3399562, ACM, July, 2020.

V. Janjic, J. Bowles, A. Vermeulen, A. Silvina, M. Belk, C. Fidas, A. Pitsillides, M. Kumar, M. Rossbory, M. Vinov, T. Given-Wilson, A. Legay, E. Blackledge, R. Arredouani, G. Stylianou, W. Huang. The SERUMS tool-chain: Ensuring security and privacy of medical data in smart patient-centric healthcare systems. Proceedings of the 2019 IEEE International Conference on Big Data (IEEE BigData 2019), pages 2726-2735, DOI 10.1109/BigData47090.2019.9005600, IEEE, February, 2020.

M. Kumar, M. Roßbory, B. Moser, B. Freudenthaler. Deriving an optimal noise adding mechanism for privacy-preserving machine learning. In G. Anderst-Kotsis, A. Tjoa, I. Khalil, E. al. (editors), Database and Expert Systems Applications - Proc DEXA 209 International Workshops, Communications in Computer and Information Science, volume 1062, pages 108-118, DOI 10.1007/978-3-030-27684-3_15, Springer, August, 2019.

G. Chasparis, M. Roßbory, V. Janjic, K. Hammond. Learning-based dynamic pinning of parallelized applications in many-core systems. Proceedings of the 27th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP 2019), pages 1-8, DOI 10.1109/EMPDP.2019.8671569, IEEE, February, 2019.

G. Chasparis, V. Janjic, M. Roßbory, K. Hammond. Learning-based dynamic pinning of parallelized applications in many-core systems. January, 2018.

G. Chasparis, M. Rossbory. Efficient dynamic pinning of parallelized applications by distributed reinforcement learning. International Journal of Parallel Programming, Special Issue on High-Level Programming for Heterogeneous Parallel Systems, volume 47, number 1, pages 24-38, DOI: 10.1007/s10766-017-0541-y, November, 2017.

G. Chasparis, M. Rossbory. Efficient dynamic pinning of parallelized applications by distributed reinforcement learning. January, 2017.

G. Chasparis, M. Roßbory, V. Janjic. Efficient dynamic pinning of parallelized applications by reinforcement learning with applications. In F. Rivera, T. Pena, J. Cabaleiro (editors), uro-Par 2017: Parallel Processing - Proc. Euro-Par 2017, Lecture Notes in Computer Science, volume 10417, pages 164-176, Springer, August, 2017.

G. Chasparis, M. Roßbory. Efficient dynamic pinning of parallelized applications by distributed reinforcement learning. pages http://arxiv.org/abs/1606.08156, June, 2016.

M. Roßbory, G. Chasparis. Parallelization of stochastic-local-search algorithms using high-level parallel patterns. January, 2016.

M. Moniruzzaman, K. Idrees, M. Roßbory, J. Gracia. An adaptive load-balancer for task-scheduling in FastFlow. Proceedings of the 5th International Conference on Advanced Communications and Computation (INFOCOMP 2015), pages 6-12, IARIA, June, 2015.

T. Grubinger, M. Roßbory, H. Schöner, M. Zwick. ModControl Springback. Technical Report, June, 2014.

M. Roßbory, W. Reisner. Parallelization of algorithms for linear discrete optimization using ParaPhrase. In F. Morvan, A. M. Toja, R. R. Wagner (editors), 24th International Workshop on Database and Expert Systems Applications, pages 241-245, CPS, August, 2013.

V. Wieser, P. Holzenspies, R. Kirner, M. Roßbory. Statistical performance analysis with dynamic workload using S-NET. January, 2012.

M. Roßbory. Konzeption und Implementierung eines zentralen Sicherheitssystems für ein verteiltes Auftragsverwaltungssystem. Master thesis, 2005.