Open karimul opened 3 years ago
Thanks! We found that HMC was unfortunately less stable than SGLD and was not really better. Would be curious to see more exploration in this direction though!
Thank you for your response.
I have a question about how to calculate fid and IS on EBM during training, because positive examples and negative examples can be totally different depend on MCMC sampling on the same step.
Sorry about the late response, to calculate fid and IS during training, I sampled 32 data points from the replay buffer.
Do you compare sampled from replay buffer to positive examples or negative examples?
To positive examples
First of all, thanks for the paper and the source code!
I'm using this repository as a baseline code trying to reproduce the result and trying to improving MCMC sampling. You give 2 option to generate sample, either using SGLD or HMC but i didn't found the result with HMC sampling. Can you share your experience with HMC? is it better than SGLD?