DeepAI AI Chat
Log In Sign Up

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

by   Fu-Chieh Chang, et al.

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.


page 8

page 13

page 14


Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach

With the rising demand for wireless services and increased awareness of ...

Synthetic Data Generation for Fraud Detection using GANs

Detecting money laundering in gambling is becoming increasingly challeng...

Sampling Strategies for GAN Synthetic Data

Generative Adversarial Networks (GANs) have been used widely to generate...

FairGen: Fair Synthetic Data Generation

With the rising adoption of Machine Learning across the domains like ban...

On the Applicability of Synthetic Data for Re-Identification

This contribution demonstrates the feasibility of applying Generative Ad...

Generalization capabilities of conditional GAN for turbulent flow under changes of geometry

Turbulent flow consists of structures with a wide range of spatial and t...

Leveraging GANs to Improve Continuous Path Keyboard Input Models

Continuous path keyboard input has higher inherent ambiguity than standa...