@article{66216, abstract = {{AbstractThe predictive performance of a machine learning model highly depends on the corresponding hyper-parameter setting. Hence, hyper-parameter tuning is often indispensable. Normally such tuning requires the dedicated machine learning model to be trained and evaluated on centralized data to obtain a performance estimate. However, in a distributed machine learning scenario, it is not always possible to collect all the data from all nodes due to privacy concerns or storage limitations. Moreover, if data has to be transferred through low bandwidth connections it reduces the time available for tuning. Model-Based Optimization (MBO) is one state-of-the-art method for tuning hyper-parameters but the application on distributed machine learning models or federated learning lacks research. This work proposes a framework$$\textit{MODES}$$MODESthat allows to deploy MBO on resource-constrained distributed embedded systems. Each node trains an individual model based on its local data. The goal is to optimize the combined prediction accuracy. The presented framework offers two optimization modes: (1)$$\textit{MODES}$$MODES-B considers the whole ensemble as a single black box and optimizes the hyper-parameters of each individual model jointly, and (2)$$\textit{MODES}$$MODES-I considers all models as clones of the same black box which allows it to efficiently parallelize the optimization in a distributed setting. We evaluate$$\textit{MODES}$$MODESby conducting experiments on the optimization for the hyper-parameters of a random forest and a multi-layer perceptron. The experimental results demonstrate that, with an improvement in terms of mean accuracy ($$\textit{MODES}$$MODES-B), run-time efficiency ($$\textit{MODES}$$MODES-I), and statistical stability for both modes,$$\textit{MODES}$$MODESoutperforms the baseline, i.e., carry out tuning with MBO on each node individually with its local sub-data set.}}, author = {{Shi, Junjie and Bian, Jiang and Richter, Jakob and Chen, Kuan-Hsun and Rahnenführer, Jörg and Xiong, Haoyi and Chen, Jian-Jia}}, issn = {{0885-6125}}, journal = {{Machine Learning}}, number = {{6}}, pages = {{1527--1547}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{MODES: model-based optimization on distributed embedded systems}}}, doi = {{10.1007/s10994-021-06014-6}}, volume = {{110}}, year = {{2021}}, } @article{66204, author = {{Yayla, Mikail and Buschjager, Sebastian and Gupta, Aniket and Chen, Jian-Jia and Henkel, Jorg and Morik, Katharina and Chen, Kuan-Hsun and Amrouch, Hussam}}, issn = {{0018-9340}}, journal = {{IEEE Transactions on Computers}}, number = {{7}}, pages = {{1681--1695}}, publisher = {{Institute of Electrical and Electronics Engineers (IEEE)}}, title = {{{FeFET-Based Binarized Neural Networks Under Temperature-Dependent Bit Errors}}}, doi = {{10.1109/tc.2021.3104736}}, volume = {{71}}, year = {{2021}}, } @article{66200, author = {{Yayla, Mikail and Buschjager, Sebastian and Gupta, Aniket and Chen, Jian-Jia and Henkel, Jorg and Morik, Katharina and Chen, Kuan-Hsun and Amrouch, Hussam}}, issn = {{0018-9340}}, journal = {{IEEE Transactions on Computers}}, number = {{7}}, pages = {{1681--1695}}, publisher = {{Institute of Electrical and Electronics Engineers (IEEE)}}, title = {{{FeFET-Based Binarized Neural Networks Under Temperature-Dependent Bit Errors}}}, doi = {{10.1109/tc.2021.3104736}}, volume = {{71}}, year = {{2021}}, } @inbook{37017, author = {{Knoll, Lisa}}, booktitle = {{Organisation und Bewertung}}, editor = {{Peetz, Thorsten and Meier, Frank}}, pages = {{49--69}}, publisher = {{Springer VS}}, title = {{{Bewerten oder Prüfen? Zur Relevanz der Figur der Prüfung für die Organisationssoziologie}}}, year = {{2021}}, } @article{66361, author = {{Len, Yoav and Ulirsch, Martin}}, issn = {{1944-7833}}, journal = {{Algebra & Number Theory}}, number = {{3}}, pages = {{785--820}}, publisher = {{Mathematical Sciences Publishers}}, title = {{{Skeletons of Prym varieties and Brill–Noethertheory}}}, doi = {{10.2140/ant.2021.15.785}}, volume = {{15}}, year = {{2021}}, } @article{66321, abstract = {{AbstractIn this article we use techniques from tropical and logarithmic geometry to construct a non-Archimedean analogue ofTeichmüller space$$\overline{{{\mathcal {T}}}}_g$$T¯gwhose points are pairs consisting of a stable projective curve over a non-Archimedean field and a Teichmüller marking of the topological fundamental group of its Berkovich analytification. This construction is closely related to and inspired by the classical construction of a non-Archimedean Schottky space for Mumford curves by Gerritzen and Herrlich. We argue that the skeleton of non-Archimedean Teichmüller space is precisely the tropical Teichmüller space introduced by Chan–Melo–Viviani as a simplicial completion of Culler–Vogtmann Outer space. As a consequence, Outer space turns out to be a strong deformation retract of the locus of smooth Mumford curves in$$\overline{{\mathcal {T}}}_g$$T¯g.}}, author = {{Ulirsch, Martin}}, issn = {{1022-1824}}, journal = {{Selecta Mathematica}}, number = {{3}}, pages = {{39}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{A non-Archimedean analogue of Teichmüller space and its tropicalization}}}, doi = {{10.1007/s00029-021-00651-4}}, volume = {{27}}, year = {{2021}}, } @article{54533, author = {{Bauer, Maike and Hohwiller, Peter}}, journal = {{Der fremdsprachliche Unterricht Englisch}}, pages = {{36--41}}, title = {{{How to tell machines what to do. Wissenschaftler(innen)biografien in einem Padlet darstellen}}}, volume = {{174}}, year = {{2021}}, } @misc{65864, author = {{Gassen, Joachim and Kosi, Urska}}, booktitle = {{Bankruptcies: A victim of the corona crisis?}}, title = {{{Bankruptcies: A victim of the corona crisis? TRR 266 Accounting for Transparency.}}}, year = {{2021}}, } @inbook{60917, author = {{Göbel, Kerstin and Frankemölle, Bernd}}, booktitle = {{Handbuch Stress und Kultur}}, isbn = {{9783658278250}}, pages = {{645--661}}, publisher = {{Springer Fachmedien Wiesbaden}}, title = {{{Interkulturalität und Wohlbefinden im Schulkontext}}}, doi = {{10.1007/987-3-658-27789-5_30}}, year = {{2021}}, }