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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows


Jul 17, 2022
Lorenz Vaitl, Kim A. Nicoli, Shinichi Nakajima, Pan Kessel

* 29 pages, 8 figures 

   Access Paper or Ask Questions

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

Path-Gradient Estimators for Continuous Normalizing Flows


Jun 17, 2022
Lorenz Vaitl, Kim A. Nicoli, Shinichi Nakajima, Pan Kessel

* 8 pages, 5 figures, 39th International Conference on Machine Learning 

   Access Paper or Ask Questions

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

Mixture-of-experts VAEs can disregard variation in surjective multimodal data


Apr 11, 2022
Jannik Wolff, Tassilo Klein, Moin Nabi, Rahul G. Krishnan, Shinichi Nakajima

* Accepted at the NeurIPS 2021 workshop on Bayesian Deep Learning 

   Access Paper or Ask Questions

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

Visualizing the diversity of representations learned by Bayesian neural networks


Jan 26, 2022
Dennis Grinwald, Kirill Bykov, Shinichi Nakajima, Marina M. -C. Höhne

* 15 pages, 13 figures 

   Access Paper or Ask Questions

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

Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse


Nov 30, 2021
Kim A. Nicoli, Christopher Anders, Lena Funcke, Tobias Hartung, Karl Jansen, Pan Kessel, Shinichi Nakajima, Paolo Stornati

* 10 pages, 2 figures, Proceedings of the 38th International Symposium on Lattice Field Theory, 26th-30th July 2021, Zoom/[email protected] Institute of Technology 

   Access Paper or Ask Questions

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

Explaining Bayesian Neural Networks


Aug 23, 2021
Kirill Bykov, Marina M. -C. Höhne, Adelaida Creosteanu, Klaus-Robert Müller, Frederick Klauschen, Shinichi Nakajima, Marius Kloft

* 16 pages, 8 figures 

   Access Paper or Ask Questions

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

NoiseGrad: enhancing explanations by introducing stochasticity to model weights


Jun 18, 2021
Kirill Bykov, Anna Hedström, Shinichi Nakajima, Marina M. -C. Höhne

* 20 pages, 11 figures 

   Access Paper or Ask Questions

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

Optimal Sampling Density for Nonparametric Regression


May 25, 2021
Danny Panknin, Shinichi Nakajima, Klaus Robert Müller

* 40 pages, plus 19 pages 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
3
>>