If you made any changes in Pure these will be visible here soon.

Personal profile

Research interests

I work on theoretically sound and practically useful machine learning. In particular, I aim to scale machine learning through parallelization. Since the amount of data-generating devices is growing rapidly, traditional cloud-based approaches to learning from their data become infeasible. Instead, pushing the learning onto - or close to - the devices allows to scale the learning, effectively use the device's computing power, minimize communication-overhead, and to protect privacy-sensitive data. For such parallelizations I seek theoretical guarantees on model quality, speedup, communication overhead, and privacy; at the same time I strive to provide practically useful software and tools.

I also work on the theoretical foundations of deep learning, seeking to understand the connections between the training process and the generalization abilities of neural networks. This is important not only for sound parallelizations, but in a broader sense for the interpretability and trustworthiness of deep learning.

Application domains I have worked on include machine learning for the automotive industry (e.g., autonomous driving), cybersecurity, biochemistry, and financial time-series.

Education/Academic qualification

Computer Science, Doctor of Philosophy (Dr. rer. nat.), Universitat Bonn (University of Bonn)

Award Date: 13 Sep 2019

Computer Science, Diplom Informatik (BSci & MSci), Universitat Bonn (University of Bonn)

Award Date: 31 Jan 2012

Research area keywords

  • Machine Learning
  • distributed optimisation
  • Parallel Computing
  • statistical learning theory
  • Deep Learning
  • Deep Learning for Cyber Security
  • co-regularization
  • Convex Optimization
  • Online Learning

Network

Recent external collaboration on country level. Dive into details by clicking on the dots or
  • HOPS: probabilistic subtree mining for small and large graphs

    Welke, P., Seiffarth, F., Kamp, M. & Wrobel, S., 2020, Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Tang, J. & Aditya Prakash, B. (eds.). New York NY USA: Association for Computing Machinery (ACM), p. 1275-1284 10 p.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    1 Citation (Scopus)
  • Resource-constrained on-device learning by dynamic averaging

    Heppe, L., Kamp, M., Adilova, L., Heinrich, D., Piatkowski, N. & Morik, K., 2020, ECML PKDD 2020 Workshops : Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020 Ghent, Belgium, September 14–18, 2020 Proceedings. Koprinska, I., Kamp, M., Appice, A., Loglisci, C., Antonie, L., Zimmermann, A., Guidotti, R. & Özgöbek, Ö. (eds.). Cham Switzerland: Springer, p. 129-144 16 p. (Communications in Computer and Information Science; vol. 1323).

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

  • Second International Workshop on Data-Centric Dependability and Security (DCDS)

    Medeiros, I., Gashi, I., Kamp, M. & Ferreira, P., 2020, 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks: Workshops, DSN-W 2020. Cotroneo, D. & Nita Rotaru, C. (eds.). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, p. XII 1 p.

    Research output: Chapter in Book/Report/Conference proceedingForeword / PostscriptOther

    Open Access
    File
  • A reparameterization-invariant flatness measure for deep neural networks

    Petzka, H., Adilova, L., Kamp, M. & Sminchisescu, C., 2019, Science meets Engineering of Deep Learning workshop at NeurIPS, 2019. Sagun, L., Gulcehre, C., Romero, A., Rostamzadeh, N. & de Freitas, N. (eds.). San Diego CA USA: Neural Information Processing Systems (NIPS), 14 p.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

    Open Access
    File
  • Efficient decentralized deep learning by dynamic model averaging

    Kamp, M., Adilova, L., Sicking, J., Hüger, F., Schlicht, P., Wirtz, T. & Wrobel, S., 2019, Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2018 Dublin, Ireland, September 10–14, 2018 Proceedings, Part I. Berlingerio, M., Bonchi, F., Gärtner, T., Hurley, N. & Ifrim, G. (eds.). Cham Switzerland: Springer, p. 393-409 17 p. (Lecture Notes in Computer Science ; vol. 11051 ).

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    11 Citations (Scopus)
If you made any changes in Pure these will be visible here soon.