Zobrazeno 1 - 10
of 16 520
pro vyhledávání: '"A. Streit"'
The gradients used to train neural networks are typically computed using backpropagation. While an efficient way to obtain exact gradients, backpropagation is computationally expensive, hinders parallelization, and is biologically implausible. Forwar
Externí odkaz:
http://arxiv.org/abs/2410.17764
Autor:
Streit, Robert, Garg, Vijay K.
Matroids provide one of the most elegant structures for algorithm design. This is best identified by the Edmonds-Rado theorem relating the success of the simple greedy algorithm to the anatomy of the optimal basis of a matroid [Edm71; Rad57]. As a re
Externí odkaz:
http://arxiv.org/abs/2408.04118
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:
Elahidoost, Parisa, Mendez, Daniel, Unterkalmsteiner, Michael, Fischbach, Jannik, Feiler, Christian, Streit, Jonathan
[Context and motivation]: Understanding and interpreting regulatory norms and inferring software requirements from them is a critical step towards regulatory compliance, a matter of significant importance in various industrial sectors. [Question/ pro
Externí odkaz:
http://arxiv.org/abs/2405.02867
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:
Streit, R. L.
The graph polynomial for the number of independent sets of size $k$ in a general undirected graph is shown to be equal to an elementary symmetric polynomial of the vertex monomials, which are determined by the edges incident at the vertices. The edge
Externí odkaz:
http://arxiv.org/abs/2312.05363
Autor:
Garg, Vijay K., Streit, Robert P.
We define a new class of predicates called equilevel predicates on a distributive lattice which eases the analysis of parallel algorithms. Many combinatorial problems such as the vertex cover problem, the bipartite matching problem, and the minimum s
Externí odkaz:
http://arxiv.org/abs/2311.06206
Autor:
Cunningham, W. Streit, Lang, Eric, Sprouster, David J., Olynik, Nicholas, Pattammattel, Ajith, Olds, Daniel, Hattar, Khalid, McCue, Ian, Trelewicz, Jason R.
A large body of literature within the additive manufacturing (AM) community has focused on successfully creating stable tungsten (W) microstructures due to significant interest in its application for extreme environments. However, solidification crac
Externí odkaz:
http://arxiv.org/abs/2311.02034