papers AI Learner
The Github is limit! Click to go to the new site.

G2R Bound: A Generalization Bound for Supervised Learning from GAN-Synthetic Data

2019-05-29
Fu-Chieh Chang, Hao-Jen Wang, Chun-Nan Chou, Edward Y. Chang

Abstract

Performing supervised learning from the data synthesized by using Generative Adversarial Networks (GANs), dubbed GAN-synthetic data, has two important applications. First, GANs may generate more labeled training data, which may help improve classification accuracy. Second, in scenarios where real data cannot be released outside certain premises for privacy and/or security reasons, using GAN- synthetic data to conduct training is a plausible alternative. This paper proposes a generalization bound to guarantee the generalization capability of a classifier learning from GAN-synthetic data. This generalization bound helps developers gauge the generalization gap between learning from synthetic data and testing on real data, and can therefore provide the clues to improve the generalization capability.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.12313

PDF

https://arxiv.org/pdf/1905.12313


Similar Posts

Comments