search

GFNOrg / EB_GFN

Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"
MIT License
73 stars 19 forks source link

Question about Evaluate MDD and NLL #2

Closed anhhndo closed 1 year ago

anhhndo commented 2 years ago

Dear Mr. Dinghuai,

Thanks for your great work.

I have a question about estimating MDD. As in (In Dai et al. (2020)), the MMD result is calculated within a fixed group of 4000 samples, which are loaded from a data file. Your work reports an average of 10 repeat results, each with 4000 samples. It looks like your code is missing some line of code to compute MMD. My question is do you still keep a fixed group of 4000 true samples and repeat sampling distinct 10 groups of GflowNets Sample. Or using distinct 10 groups of 4000 true samples. And, for NLL do you keep 4000 true samples fixed or not.

Thanks Mr. Dinghuai

Untitled
zdhNarsil commented 1 year ago

We use distinct 10 groups of 4000 true samples for MMD. Hope this helps!