Fetching the paper…

Reading the bibliography…

2018

On the Implicit Assumptions of GANs

Li, Ke, Malik, Jitendra

Original
PDF
Post on X

Understand

Generative adversarial nets (GANs) have generated a lot of excitement.

Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees.
A number of enlightening papers have pointed out that these issues arise from unjustified assumptions that are commonly made, but the message seems to have been lost amid the optimism of recent years.
We believe the identified problems deserve more attention, and highlight the implications on both the properties of GANs and the trajectory of research on probabilistic models.

On the Implicit Assumptions of GANs · Around

Built on

Monte carlo methods of inference for implicit statistical models
Diggle, Peter J and Gratton, Richard J · 1984
Earlier work this paper cites.
Generative adversarial nets
Goodfellow, Ian, Pouget-Abadie, Jean, Mirza, Mehdi, Xu, Bing, Warde-Farley, David, Ozair, Sherjil, Courville, Aaron, and Bengio, Yoshua · 2014
Earlier work this paper cites.
On distinguishability criteria for estimating generative models
Original
Goodfellow, Ian J · 2014
Earlier work this paper cites.
Likelihood-free inference via classification
Original
Gutmann, Michael U, Dutta, Ritabrata, Kaski, Samuel, and Corander, Jukka · 2014
Earlier work this paper cites.

Similar

How (not) to train your generative model: Scheduled sampling, likelihood, adversary?
Original
Huszár, Ferenc · 2015
Cited alongside, same era.
Learning in implicit generative models
Original
Mohamed, Shakir and Lakshminarayanan, Balaji · 2016
Cited alongside, same era.
f-GAN: Training generative neural samplers using variational divergence minimization
Nowozin, Sebastian, Cseke, Botond, and Tomioka, Ryota · 2016
Cited alongside, same era.
Towards principled methods for training generative adversarial networks
Original
Arjovsky, Martin and Bottou, Léon · 2017
Cited alongside, same era.

Then

Generalization and equilibrium in generative adversarial nets (GANs)
Original
Arora, Sanjeev, Ge, Rong, Liang, Yingyu, Ma, Tengyu, and Zhang, Yi · 2017
Later among the works it cites.
Non-parametric estimation of jensen-shannon divergence in generative adversarial network training
Original
Sinn, Mathieu and Rawat, Ambrish · 2017
Later among the works it cites.
Towards a testable notion of generalization for generative adversarial networks
Cornish, Robert, Yang, Hongseok, and Wood, Frank · 2018
Closest in time.
Implicit maximum likelihood estimation
Original
Li, Ke and Malik, Jitendra · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…