Severin Reiz

Technical University of Munich

TUM School of CIT
Department of Computer Science
Boltzmannstrasse 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

The Book Software for Exascale Computing - SPPEXA 2016-2019, has been published!

News-SR, News |

The DFG Priority project "Software for Exascale Computing (SPPEXA)" has been coordinated by the SCCS group around Prof. Bungartz. Funding is running out in December 2020, and recently we have published a an open access book as final report.

This open access book summarizes the research done and results obtained in the second funding phase of SPPEXA.
In that respect, it both represents a continuation of Vol. 113 in Springer’s series Lecture Notes in Computational Science and Engineering, the corresponding report of SPPEXA’s first funding phase, and provides an overview of SPPEXA’s contributions towards exascale computing in today's sumpercomputer technology. The individual chapters address one or more of the research directions (1) computational algorithms, (2) system software, (3) application software, (4) data management and exploration, (5) programming, and (6) software tools.

The book has an interdisciplinary appeal: scholars from computational sub-fields in computer science, mathematics, physics, or engineering will find it of particular interest.

.


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

  • Maximilian Jokel: Evaluating acceleration models and respective stochasticity towards a real-time forecasting model for landslides. Masterarbeit, 2023 mehr…
  • Maximilian Forstenhaeusler: Physics-Informed Geometric Deep Learning for Molecular Property Prediction. Masterarbeit, 2023 mehr…
  • František Deckert: Machine Learning in the Context of a Real-Time Education in Gaming. Masterarbeit, 2023 mehr…
  • Andreas Dachsberger: Decentralized Mutual Exclusion for Mobile Robots at Shared Resources in Complex. Masterarbeit, 2023 mehr…
  • Danylo Movchan: Implementing a learning-rate scheduler in a Newton-CG Optimizer for Deep Learning. Bachelorarbeit, 2022 mehr…
  • Osama Alhartani: Transfer Learning and Dynamic Loading in TUM-Lens. Masterarbeit, 2022 mehr…
  • Keerthi Gaddameedi: Efficient and Scalable Kernel Matrix Approximation using Hierarchical Decomposition. Masterarbeit, 2022 mehr…
  • Keerthi Gaddameedi: Efficient and Scalable Kernel Matrix Approximation using Hierarchical Decomposition. Masterarbeit, 2022 mehr…
  • Hanna Weigold: Second-Order Optimization Methods for Bayesian Neural Networks. Masterarbeit, 2021 mehr…
  • Tao Xiang: Extending a Newton-CG Second-order Optimizer to Natural Language Processing. Bachelorarbeit, 2021 mehr…
  • Mihai Zorca: Training Deep Convolutional Neural Networks on the GPU Using a Second-Order Optimizer. Bachelorarbeit, 2020 mehr…
  • Maximilian Jokel: Implementing a TensorFlow-Slim based Android app for image classification. Bachelorarbeit, 2020 mehr…
  • Julian Suk: Application of second-order optimisation for large-scale deep learning. Masterarbeit, 2020 mehr…
  • Oriolson Rodriguez Ramirez: Integrated approach of Random Projections and Sparse Grids for Density estimation. Masterarbeit, 2020 mehr…
  • Tianyi Ge: Python Software Suite of Geometric-Oblivious FMM. IDP-Arbeit, 2020 mehr…
  • Eric Fuchs: Comparison of distance metrics for MDS based NLDR using CNNs. Bachelorarbeit, 2020 mehr…

Teaching

Winter semester 2020/21

Summer semester 2020

Publications

  • Gaddameedi, Keerthi; Reiz, Severin; Neckel, Tobias; Bungartz, Hans-Joachim: Efficient and Scalable Kernel Matrix Approximations Using Hierarchical Decomposition. In: Intelligent Computers, Algorithms, and Applications. Springer Nature Singapore, 2024 mehr…
  • Severin Reiz; Tobias Neckel; Hans-Joachim Bungartz;: Neural Nets with a Newton Conjugate Gradient Method on Multiple GPUs. In Proceedings of the 14th International Conference on Parallel Processing and Applied Mathematics, 2022, 13 mehr…
  • 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 mehr…
  • 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. (Hrsg.): Springer International Publishing, 2020 mehr…
  • Hans-Joachim Bungartz; Severin Reiz; Benjamin Uekermann; Philipp Neumann; Wolfgang E. Nagel: Hans-Joachim Bungartz; Severin Reiz; Benjamin Uekermann; Philipp Neumann; Wolfgang Nagel (Hrsg.): Software for Exascale Computing - SPPEXA 2016-2019. Band LNCSE 136. Lecture Notes in Computational Science and Engineering (LNCSE) 136. Springer, 2020 mehr…
  • 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 mehr…
  • 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 mehr…
  • 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 mehr…
  • Reiz, Severin: Black Box Hierarchical Approximations for SPD Matrices. Master's thesis, 2017 mehr…
  • Saumitra Joshi; Juan Carlos Medina; Friedrich Menhorn; Severin Reiz; Benjamin Rüth; Erik Wannerberg; Anna Yurova: CAD-integrated Topology Optimization (BGCE Honours Project). , 2016 mehr…
  • Severin Reiz: CFD Study of Fuel-air Mixing in a Novel Low-NOx Burner. Projektarbeit, 2015 mehr…
  • Reiz, Severin: Water Injections in Gas Turbines - Kinetic Modeling with Cantera. Bachelor's thesis, 2014 mehr…

Talks

  • Severin Reiz: SPPEXA and beyond: Perspectives of Exascale Computing in the Context of AI. Human-centric Artificial Intelligence, 20202nd French-German-Japanese Symposium mehr…
  • Severin Reiz: Some words from SPPEXA. (Vortrag / Parallel Programming Models - Productivity and Applications for Exascale and Beyond - 4th edition) 2019 mehr…
  • Severin Reiz: A Fast Multipole Method for Training Neural Networks. PhD Forum: IEEE International Supercomputing Conference, 2019 mehr…
  • Severin Reiz: Numerical approaches to large-scale machine learning. (Vortrag / Leogang High Performance Computing Workshop) 2019 mehr…
  • 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 mehr…

Posters

  • Severin Reiz; Tobias Neckel; Hans-Joachim Bungartz: Training Large-Scale Neural Networks with a Newton Conjugate Gradient Method (Newton-CG). SIAM Conference on Computational Science and Engineering (CSE23), 2023Amsterdam mehr…
  • 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) mehr…
  • 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 mehr…
  • Reiz, Severin; Biros, George; Bungartz, Hans-Joachim: Nonsymmetric Algebraic Fast Multipole Method. Computational Science at Scale (CoSaS) 2018, 2018 mehr…