As in the estimation theory, more samples can help to enhance the accuracy of the estimation. If we only get a small amount of samples at first, we then use these samples to train a generative adversarial network (GAN) and generate more mimic samples with this GAN, can we add the generating samples with the original samples to enhance the estimation?

E.g., the authors in the paper use GAN to enhance the lease square estimator. https://scihub.wikicn.top/10.1109/tccn.2020.3013257


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.