Refine
Year of publication
- 2020 (36) (remove)
Document Type
- Article (unreviewed) (36) (remove)
Has Fulltext
- no (36)
Is part of the Bibliography
- yes (36) (remove)
Keywords
- Export (2)
- Finance (2)
- Projektmanagement (2)
- Trade (2)
- Bildungsmanagement (1)
- COVID-19 (1)
- Climate (1)
- Covid-19 (1)
- Datenschutz (1)
- Deckungsbeitrag (1)
Institute
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (13)
- Fakultät Wirtschaft (W) (11)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (9)
- IMLA - Institute for Machine Learning and Analytics (5)
- IfTI - Institute for Trade and Innovation (4)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (3)
- INES - Institut für nachhaltige Energiesysteme (1)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (1)
Open Access
- Closed Access (17)
- Open Access (14)
Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss surface through its Hessian eigenvalues, and show that mode collapse is related to the convergence towards sharp minima. In particular, we observe how the eigenvalues of the G are directly correlated with the occurrence of mode collapse. Finally, motivated by these findings, we design a new optimization algorithm called nudged-Adam (NuGAN) that uses spectral information to overcome mode collapse, leading to empirically more stable convergence properties.
With economic weight shifting toward net zero, now is the time for ECAs, Exim-Banks, and PRIs to lead. Despite previous success, aligning global economic governance to climate goals requires additional activities across export finance and investment insurance institutions. The new research project initiated by Oxford University, ClimateWorks Foundation, and Mission 2020 including other practitioners and academics from institutions such as Atradius DSB, Columbia University, EDC, FMO and Offenburg University focuses on reshaping future trade and investment governance in light of climate action. The idea of a ‘Berne Union Net Zero Club’ is an important item in a potential package of reforms. This can include realigning mandates and corporate strategies, principles of intervention, as well as ECA, Exim-Bank and PRI operating models in order to accelerate net zero transformation. Full transparency regarding Berne Union members’ activities would be an excellent starting point. We invite all interested parties in the sector to come together to chart our own path to net zero
Die Coronakrise hat weltweit das Wirtschafts- und Gesellschaftsleben in bisher ungekannter Weise verändert. Die ohnehin bereits komplexen Herausforderungen in Zeiten des Klimawandels sind damit noch gestiegen. Genossenschaftliche Innovationsökosysteme können Lösungsansätze für die gravierenden Veränderungen im unternehmerischen, kommunalen und gesellschaftlichen Umfeld schaffen.