Die Seminar kann wie geplant stattfinden (dies hing bis letzte Woche noch an meiner fristgerechten Berufung an die FU zum SS2021;-), *Leider* erstmal virtuell. Beginn ist nun Do, 15.04.2020, 10-12h:

https://fu-berlin.webex.com/fu-berlin-en/j.php?MTID=m41f79f367efc17f5bf8a4cb79cd7f10c

 

Hier soll eine erste grobe Orientierung zum Seminar stattfinden. Thematisch wollen wir uns auf das Thema GAN, (variational) Autoencoder, ...  insbesondere mit implizitem Transinformationsschätzer (z.B. InfoGAN) und Datenschutz fokussieren. Es passt sehr gut zur VL 'Infotheoretische Grundlagen von Identität und Datenschutz'.

 

 

Mögliche Themen:

1. Mutual Information Neural Estimation

Belghazi, Mohamed Ishmael, et al. "Mutual information neural estimation." International Conference on Machine Learning. PMLR, 2018.

2. Variational Autoencoder

Kingma, Diederik P., and Max Welling. "Auto-encoding variational bayes." arXiv preprint arXiv:1312.6114 (2013).

3. InfoGAN

Chen, Xi, et al. "Infogan: Interpretable representation learning by information maximizing generative adversarial nets." arXiv preprint arXiv:1606.03657 (2016).

4. Wasserstein GAN

Arjovsky, Martin, Soumith Chintala, and Léon Bottou. "Wasserstein generative adversarial networks." International conference on machine learning. PMLR, 2017.

5. Deep Infomax

Hjelm, R. Devon, et al. "Learning deep representations by mutual information estimation and maximization." arXiv preprint arXiv:1808.06670 (2018).

6. BiGAN

Donahue, Jeff, Philipp Krähenbühl, and Trevor Darrell. "Adversarial feature learning." arXiv preprint arXiv:1605.09782 (2016).

7. Understanding the limitations of variational mutual information estimators

Song, Jiaming, and Stefano Ermon. "Understanding the limitations of variational mutual information estimators." arXiv preprint arXiv:1910.06222 (2019).
 
8. Bridging the gap between f-GANs and Wasserstein GANs
 
Song, Jiaming, and Stefano Ermon. "Bridging the gap between f-gans and wasserstein gans." International Conference on Machine Learning. PMLR, 2020.
 
9. Deep variational information bottleneck
 
Alemi, Alexander A., et al. "Deep variational information bottleneck." arXiv preprint arXiv:1612.00410 (2016).
 
10. Deep learning for the Gaussian wiretap channel
 
Fritschek, Rick, Rafael F. Schaefer, and Gerhard Wunder. "Deep learning for the Gaussian wiretap channel." ICC 2019-2019 IEEE International Conference on Communications (ICC). IEEE, 2019.