Bayesian GAN — mentioned by xcodevn

Fri, 10 Nov 2017 02:49:10 GMT

If you read the paper https://arxiv.org/abs/1705.09558, in section 2.1, it defines two conditional posteriors for the parameters of the generator and discriminator. Then, classical GAN is just a maximum likelihood estimate (or, a MAP estimate with uniform prior) of the parameters. Next, the paper said: how about sampling the whole posterior distribution instead of finding only one point of maximum likelihood as classical GANs do. This is the point where the famous Markov chain Monte Carlo (MCMC) algorithms become useful. They use something called stochastic gradient Hamiltonian Monte Carlo…

Paper and discussion history. A mention is not an endorsement.

Bayesian GAN · HackerPapers discussions

Bayesian GAN — mentioned by xcodevn