DeepAI AI Chat
Log In Sign Up

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

05/29/2019
by   Fu-Chieh Chang, et al.
0

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.

READ FULL TEXT

page 8

page 13

page 14

02/01/2023

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 ...
09/26/2021

Synthetic Data Generation for Fraud Detection using GANs

Detecting money laundering in gambling is becoming increasingly challeng...
09/10/2019

Sampling Strategies for GAN Synthetic Data

Generative Adversarial Networks (GANs) have been used widely to generate...
10/24/2022

FairGen: Fair Synthetic Data Generation

With the rising adoption of Machine Learning across the domains like ban...
12/20/2022

On the Applicability of Synthetic Data for Re-Identification

This contribution demonstrates the feasibility of applying Generative Ad...
02/20/2023

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...
04/06/2020

Leveraging GANs to Improve Continuous Path Keyboard Input Models

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