Gradient penalty from a maximum margin perspective.

By Alexia Jolicoeur-Martineau, Ioannis Mitliagkas. 2020

11 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Sergey Levine
2. Peter R. Florence
3. Andy Zeng
4. Corey Lynch
5. Jonathan Tompson
6. Johnny Lee
7. Ayzaan Wahid
8. Yilun Du

Citations in the corpus

• Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network (2020, neutral): “Follow up work has analysed the penalty in more detail and concluded that, contrary to our case, for training Wasserstein GANS the one-sided penalty is preferable theoretically and practically (Jolicoeur-Martineau & Mitliagkas, 2019; Petzka et al., 2017).”
• Implicit Behavioral Cloning (2021, methodology): “We use either a) a 51 derivative-free (sampling-based) optimization procedure, b) an auto-regressive variant of the derivative-free 52 optimizer which performs coordinate descent, or c) gradient-based Langevin sampling [11, 12] with gradient 53 penalty [20] loss during training – see the Appendix fo”