Evaluating GANs via Duality
By Paulina Grnarova, Kfir Yehuda Levy, Aurélien Lucchi, Nathanael Perraudin, Thomas Hofmann, Andreas Krause. 2018
8 citations recorded by the source corpus.
Generative Adversarial Networks (GANs) have shown great results in accurately modeling complex distributions, but their training is known to be difficult due to instabilities caused by a challenging minimax optimization problem. This is especially troublesome given the lack of an evaluation metric that can reliably detect non-convergent behaviors. We leverage the notion of duality gap from game theory in order to propose a novel convergence metric for GANs that has low computational cost. We verify the validity of the proposed metric for various test scenarios commonly used in the literature.
Subfields: Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Generative Models
- Subbarao Kambhampati
- Niharika Jain
- Lydia Manikonda
- Aurélien Lucchi
- Sailik Sengupta
- Alberto Olmo Hernandez
- Stefan Woerner
- Christa Zoufal
Citations in the corpus
- Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses (2020, background): “While mode collapse is a well-studied phenomenon (Grnarova et al., 2018; Goodfellow, 2016; Che et al., 2017; Arora et al., 2017) and several GAN variants have been developed to alleviate its effects (Metz et al., 2017; Srivastava et al., 2017; Arjovsky et al., 2017; Miyato et al., 2018; Tolstikhin…”
- Quantum Generative Adversarial Networks for learning and loading random distributions (2019, background): “[41] P.”