Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Picture for Carl-Johann Simon-Gabriel

Carl-Johann Simon-Gabriel

Bridging the Gap to Real-World Object-Centric Learning


Sep 29, 2022
Maximilian Seitzer, Max Horn, Andrii Zadaianchuk, Dominik Zietlow, Tianjun Xiao, Carl-Johann Simon-Gabriel, Tong He, Zheng Zhang, Bernhard Schölkopf, Thomas Brox, Francesco Locatello


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Targeted Separation and Convergence with Kernel Discrepancies


Sep 26, 2022
Alessandro Barp, Carl-Johann Simon-Gabriel, Mark Girolami, Lester Mackey


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Assaying Out-Of-Distribution Generalization in Transfer Learning


Jul 19, 2022
Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler, Carl-Johann Simon-Gabriel, Max Horn, Dominik Zietlow, David Kernert, Chris Russell, Thomas Brox, Bernt Schiele, Bernhard Schölkopf, Francesco Locatello


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PopSkipJump: Decision-Based Attack for Probabilistic Classifiers


Jun 14, 2021
Carl-Johann Simon-Gabriel, Noman Ahmed Sheikh, Andreas Krause

* ICML'21. Code available at https://github.com/cjsg/PopSkipJump . 9 pages & 7 figures in main part, 14 pages & 10 figures in appendix 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Metrizing Weak Convergence with Maximum Mean Discrepancies


Jun 16, 2020
Carl-Johann Simon-Gabriel, Alessandro Barp, Lester Mackey

* 10 pages. Correction of Thm.12 in Simon-Gabriel and Sch\"olkopf, JMLR, 19(44):1-29, 2018. See http://jmlr.org/papers/v19/16-291.html 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adversarial Vulnerability of Neural Networks Increases With Input Dimension


Oct 08, 2018
Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou, Bernhard Schölkopf, David Lopez-Paz

* 10 pages main text and references, 8 pages appendix, 7 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

AdaGAN: Boosting Generative Models


May 24, 2017
Ilya Tolstikhin, Sylvain Gelly, Olivier Bousquet, Carl-Johann Simon-Gabriel, Bernhard Schölkopf

* Updated with MNIST pictures and discussions + Unrolled GAN experiments 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

From optimal transport to generative modeling: the VEGAN cookbook


May 22, 2017
Olivier Bousquet, Sylvain Gelly, Ilya Tolstikhin, Carl-Johann Simon-Gabriel, Bernhard Schoelkopf


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Consistent Kernel Mean Estimation for Functions of Random Variables


Oct 19, 2016
Carl-Johann Simon-Gabriel, Adam Ścibior, Ilya Tolstikhin, Bernhard Schölkopf

* NIPS 2016 Proceedings (p. 1732-1740) 
* 17 pages including appendix 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributions


Apr 18, 2016
Carl-Johann Simon-Gabriel, Bernhard Schölkopf

* 55 pages (33 pages main text, 22 pages appendix), 2 tables, 1 figure (in appendix) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>