TY - GEN
T1 - Realizing GANs via a Tunable Loss Function
AU - Kurri, Gowtham R.
AU - Sypherd, Tyler
AU - Sankar, Lalitha
N1 - Funding Information:
This work is supported in part by NSF grants CIF-1901243, CIF-2007688, and CIF-2134256. 1We refer to the GAN introduced by Goodfellow et al. [1] as vanilla GAN, as done in the literature [2], [3] to distinguish it from others introduced later.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - We introduce a tunable GAN, called α-GAN, parameterized by α(0, ∞], which interpolates between various f-GANs and Integral Probability Metric based GANs (under constrained discriminator set). We construct α- GAN using a supervised loss function, namely, α- loss, which is a tunable loss function capturing several canonical losses. We show that α- GAN is intimately related to the Arimoto divergence, which was first proposed by Österriecher (1996), and later studied by Liese and Vajda (2006). We posit that the holistic understanding that α- GAN introduces will have practical benefits of addressing both the issues of vanishing gradients and mode collapses.
AB - We introduce a tunable GAN, called α-GAN, parameterized by α(0, ∞], which interpolates between various f-GANs and Integral Probability Metric based GANs (under constrained discriminator set). We construct α- GAN using a supervised loss function, namely, α- loss, which is a tunable loss function capturing several canonical losses. We show that α- GAN is intimately related to the Arimoto divergence, which was first proposed by Österriecher (1996), and later studied by Liese and Vajda (2006). We posit that the holistic understanding that α- GAN introduces will have practical benefits of addressing both the issues of vanishing gradients and mode collapses.
UR - http://www.scopus.com/inward/record.url?scp=85123415146&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123415146&partnerID=8YFLogxK
U2 - 10.1109/ITW48936.2021.9611499
DO - 10.1109/ITW48936.2021.9611499
M3 - Conference contribution
AN - SCOPUS:85123415146
T3 - 2021 IEEE Information Theory Workshop, ITW 2021 - Proceedings
BT - 2021 IEEE Information Theory Workshop, ITW 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Information Theory Workshop, ITW 2021
Y2 - 17 October 2021 through 21 October 2021
ER -