Severin Reiz

Technical University of Munich

Department of Informatics
Boltzmannstr. 3
85748 Garching
Germany

Office: MI 02.05.058
Mail: reiz (at) in.tum.de
Tel: +49-89-289-18603
Office Hours: by arrangement

 

Background

  • Doctoral candidate, TUM Graduate School - IGSSE
  • Research Associate (Wissenschaftlicher Mitarbeiter) at TUM SCCS since July 2017
  • M.Sc. with Honours in Computational Science and Engineering, Technical University of Munich, 2017
    • M. Sc. Thesis at University of Texas at Austin, USA (George Biros)
    • Seminar Thesis at Norwegian University of Science and Technology, Trondheim and SINTEF
  • B.Sc. Engineering Science, Technical University of Munich, 2014

News

Best Poster Award at CoSaS 2018

News-SR, News, News-IJB |

Ivana Jovanovic and Severin Reiz scored the 1st and 2nd place in the Best Poster Jury Award at CoSaS meeting in Erlangen, Germany, among 70 posters. The titles of the posters are "3D Deep Learning in High Resolution Point Clouds" and "Nonsymmetric geometry-oblivious fast multipole method".

Ivana Jovanovic and Severin Reiz scored the 1st and 2nd place in the Best Poster Jury Award at CoSaS meeting in Erlangen, Germany, among 70 posters. The titles of the posters are "3D Deep Learning in High Resolution Point Clouds" and "Nonsymmetric geometry-oblivious fast multipole method".


Research projects

  • Program Manager of SPPEXA (2018-2020).
  • Developer in the ExaNIML project

Open and running student projects


Topics change (frequently) with my ongoing work and depend mostly on the interests and experience of the student. It is best to contact me directly if you are interested in a thesis or student project.

See also the list of Student Projects at our chair.

Do you want to know what other students are working on in our chair? You are warmly encouraged to attend their presentations at the SCCS Colloquium! Come to get ideas, meet your potential supervisor, or to learn from the style of others for your own presentation.

Open student projects

Running student projects

We are working on an android app for live image classification (locally on your device). Feel free to download the Android package (apk)

Past student projects and Theses advised

  • Hanna Weigold: Second-Order Optimization Methods for Bayesian Neural Networks. Master thesis, 2021 more…
  • Tao Xiang: Extending a Newton-CG Second-order Optimizer to Natural Language Processing. Bachelor thesis, 2021 more…
  • Mihai Zorca: Training Deep Convolutional Neural Networks on the GPU Using a Second-Order Optimizer. Bachelor thesis, 2020 more…
  • Maximilian Jokel: Implementing a TensorFlow-Slim based Android app for image classification. Bachelor thesis, 2020 more…
  • Julian Suk: Application of second-order optimisation for large-scale deep learning. Master thesis, 2020 more…
  • Oriolson Rodriguez Ramirez: Integrated approach of Random Projections and Sparse Grids for Density estimation. Master thesis, 2020 more…
  • Tianyi Ge: Python Software Suite of Geometric-Oblivious FMM. IDP-Arbeit, 2020 more…
  • Eric Fuchs: Comparison of distance metrics for MDS based NLDR using CNNs. Bachelor thesis, 2020 more…

Teaching

Winter semester 2020/21

Summer semester 2020

Publications

  • Chao Chen; Severin Reiz; Chenhan Yu; Hans-Joachim Bungartz; George Biros;: Fast Evaluation and Approximation of the Gauss-Newton Hessian Matrix for the Multilayer Perceptron. SIAM Journal on Matrix Analysis and Applications, 2021 more…
  • Bungartz, Hans-Joachim; Nagel, Wolfgang E.; Neumann, Philipp; Reiz, Severin; Uekermann, Benjamin: Software for Exascale Computing: Some Remarks on the Priority Program SPPEXA. In: Bungartz, Hans-Joachim; Reiz, Severin; Uekermann, Benjamin; Neumann, Philipp; Nagel, Wolfgang E. (Ed.): Springer International Publishing, 2020 more…
  • Hans-Joachim Bungartz; Severin Reiz; Benjamin Uekermann; Philipp Neumann; Wolfgang E. Nagel: Hans-Joachim Bungartz; Severin Reiz; Benjamin Uekermann; Philipp Neumann; Wolfgang Nagel (Ed.): Software for Exascale Computing - SPPEXA 2016-2019. Volume LNCSE 136. Lecture Notes in Computational Science and Engineering (LNCSE) 136. Springer, 2020 more…
  • Chao Chen; Severin Reiz; Chenhan Yu, Hans-Joachim Bungartz; George Biros: H-matrix approximation of the Gauss-Newton Hessian matrix for the multilayer perceptron. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 2019 more…
  • Chenhan Yu; Severin Reiz; George Biros: Distributed O(N) Linear Solver for Dense Symmetric Hierarchical Semi-Separable Matrices. Embedded Multicore/Many-core Systems on a chip, IEEE, 2019 more…
  • Yu, Chenhan D.; Reiz, Severin; Biros, George: Distributed-Memory Hierarchical Compression of Dense SPD Matrices. SC '18: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2018 more…
  • Reiz, Severin: Black Box Hierarchical Approximations for SPD Matrices. Master's thesis, 2017 more…
  • Saumitra Joshi; Juan Carlos Medina; Friedrich Menhorn; Severin Reiz; Benjamin Rüth; Erik Wannerberg; Anna Yurova: CAD-integrated Topology Optimization (BGCE Honours Project). , 2016 more…
  • Severin Reiz: CFD Study of Fuel-air Mixing in a Novel Low-NOx Burner. Projekt thesis, 2015 more…
  • Reiz, Severin: Water Injections in Gas Turbines - Kinetic Modeling with Cantera. Bachelor's thesis, 2014 more…

Talks

  • Severin Reiz: SPPEXA and beyond: Perspectives of Exascale Computing in the Context of AI. Human-centric Artificial Intelligence, 20202nd French-German-Japanese Symposium more…
  • Severin Reiz: Some words from SPPEXA. (Talk / Parallel Programming Models - Productivity and Applications for Exascale and Beyond - 4th edition) 2019 more…
  • Severin Reiz: A Fast Multipole Method for Training Neural Networks. PhD Forum: IEEE International Supercomputing Conference, 2019 more…
  • Severin Reiz: Numerical approaches to large-scale machine learning. (Talk / Leogang High Performance Computing Workshop) 2019 more…
  • Severin Reiz: Second-order optimization for AI using HSS Matrices on distributed-memory setup. Convergence of HPC and Data Science for Future Extreme Scale Intelligent Applications, 2019 more…

Posters

  • Severin Reiz; Hasan Ashraf; Tobias Neckel; George Biros; Hans-Joachim Bungartz;: An Exascale Library for Numerically Inspired Machine Learning (ExaNIML). ISC High Performance, 2020Frankfurt (DIGITAL due corona) more…
  • Severin Reiz; Tobias Neckel; Hans-Joachim Bungartz; George Biros: ExaNIML: An Exascale Library for Numerically Inspired Machine Learning. 13th IGSSE Forum, Raitenhaslach, 201913th IGSSE Forum, Raitenhaslach more…
  • Reiz, Severin; Biros, George; Bungartz, Hans-Joachim: Nonsymmetric Algebraic Fast Multipole Method. Computational Science at Scale (CoSaS) 2018, 2018 more…