What is an intuitive explanation for the Importance Weighted Autoencoder?



I have been reading a paper by Burda et al. on Importance Weighted Autoencoders(IWAE) but I can't quite grasp what they mean by sampling the terms h1...hk. Do they mean you have separate models from which you sample and then average over?


Posted 2018-10-03T10:07:40.587

Reputation: 21

post something more from the paper explaining what are those terms – Francesco Pegoraro – 2018-10-03T12:58:35.217

No answers