Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Streit, Achim"'
Autor:
Weyrauch, Arvid, Steens, Thomas, Taubert, Oskar, Hanke, Benedikt, Eqbal, Aslan, Götz, Ewa, Streit, Achim, Götz, Markus, Debus, Charlotte
Transformers have recently gained prominence in long time series forecasting by elevating accuracies in a variety of use cases. Regrettably, in the race for better predictive performance the overhead of model architectures has grown onerous, leading
Externí odkaz:
http://arxiv.org/abs/2405.03429
Autor:
Coquelin, Daniel, Flügel, Katherina, Weiel, Marie, Kiefer, Nicholas, Öz, Muhammed, Debus, Charlotte, Streit, Achim, Götz, Markus
Communication bottlenecks severely hinder the scalability of distributed neural network training, particularly in high-performance computing (HPC) environments. We introduce AB-training, a novel data-parallel method that leverages low-rank representa
Externí odkaz:
http://arxiv.org/abs/2405.01067
Autor:
Horzela, Maximilian, Casanova, Henri, Giffels, Manuel, Gottmann, Artur, Hofsaess, Robin, Quast, Günter, Tisbeni, Simone Rossi, Streit, Achim, Suter, Frédéric
Publikováno v:
EPJ Web of Conf. 295 (2024) 04032
Predicting the performance of various infrastructure design options in complex federated infrastructures with computing sites distributed over a wide area network that support a plethora of users and workflows, such as the Worldwide LHC Computing Gri
Externí odkaz:
http://arxiv.org/abs/2403.14903
Autor:
Coquelin, Daniel, Flügel, Katharina, Weiel, Marie, Kiefer, Nicholas, Debus, Charlotte, Streit, Achim, Götz, Markus
This study explores the learning dynamics of neural networks by analyzing the singular value decomposition (SVD) of their weights throughout training. Our investigation reveals that an orthogonal basis within each multidimensional weight's SVD repres
Externí odkaz:
http://arxiv.org/abs/2401.08505
Autor:
Bruers, Ben, Cruces, Marilyn, Demleitner, Markus, Duckeck, Guenter, Düren, Michael, Eich, Niclas, Enßlin, Torsten, Erdmann, Johannes, Erdmann, Martin, Fackeldey, Peter, Felder, Christian, Fischer, Benjamin, Fröse, Stefan, Funk, Stefan, Gasthuber, Martin, Grimshaw, Andrew, Hadasch, Daniela, Hannemann, Moritz, Kappes, Alexander, Kleinemühl, Raphael, Kozlov, Oleksiy M., Kuhr, Thomas, Lupberger, Michael, Neuhaus, Simon, Niknejadi, Pardis, Reindl, Judith, Schindler, Daniel, Schneidewind, Astrid, Schreiber, Frank, Schumacher, Markus, Schwarz, Kilian, Streit, Achim, von Cube, R. Florian, Walker, Rod, Walther, Cyrus, Wozniewski, Sebastian, Zhou, Kai
Given the urgency to reduce fossil fuel energy production to make climate tipping points less likely, we call for resource-aware knowledge gain in the research areas on Universe and Matter with emphasis on the digital transformation. A portfolio of m
Externí odkaz:
http://arxiv.org/abs/2311.01169
Autor:
Flügel, Katharina, Coquelin, Daniel, Weiel, Marie, Debus, Charlotte, Streit, Achim, Götz, Markus
Backpropagation has long been criticized for being biologically implausible, relying on concepts that are not viable in natural learning processes. This paper proposes an alternative approach to solve two core issues, i.e., weight transport and updat
Externí odkaz:
http://arxiv.org/abs/2304.13372
Autor:
Taubert, Oskar, Weiel, Marie, Coquelin, Daniel, Farshian, Anis, Debus, Charlotte, Schug, Alexander, Streit, Achim, Götz, Markus
We present Propulate, an evolutionary optimization algorithm and software package for global optimization and in particular hyperparameter search. For efficient use of HPC resources, Propulate omits the synchronization after each generation as done i
Externí odkaz:
http://arxiv.org/abs/2301.08713
Autor:
Kahn, James, Tsaklidis, Ilias, Taubert, Oskar, Reuter, Lea, Dujany, Giulio, Boeckh, Tobias, Thaller, Arthur, Goldenzweig, Pablo, Bernlochner, Florian, Streit, Achim, Götz, Markus
In this work, we present a neural approach to reconstructing rooted tree graphs describing hierarchical interactions, using a novel representation we term the Lowest Common Ancestor Generations (LCAG) matrix. This compact formulation is equivalent to
Externí odkaz:
http://arxiv.org/abs/2208.14924
Autor:
Coquelin, Daniel, Rasti, Behnood, Götz, Markus, Ghamisi, Pedram, Gloaguen, Richard, Streit, Achim
As with any physical instrument, hyperspectral cameras induce different kinds of noise in the acquired data. Therefore, Hyperspectral denoising is a crucial step for analyzing hyperspectral images (HSIs). Conventional computational methods rarely use
Externí odkaz:
http://arxiv.org/abs/2204.06979
Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)
Autor:
Coquelin, Daniel, Debus, Charlotte, Götz, Markus, von der Lehr, Fabrice, Kahn, James, Siggel, Martin, Streit, Achim
Publikováno v:
J Big Data 9, 14 (2022)
With increasing data and model complexities, the time required to train neural networks has become prohibitively large. To address the exponential rise in training time, users are turning to data parallel neural networks (DPNN) to utilize large-scale
Externí odkaz:
http://arxiv.org/abs/2104.05588