chunyuanli / psgld Goto Github PK

Thanks for sharing your code!

Your paper mentions about the prior on the parameters being , and that the variance () is set to 1 by default for DNN experiments and in some scenario it is set to 100. But I couldn't find it reflected anywhere in the code. Am I missing something obvious?

Hi,

I was trying to run test_FNN_mnist.m but I got the following error:
" Undefined function or variable 'environmentVariables'. "
Can you tell me to fix it?

Thanks

In SGLD_RMSprop.m the noise is scaled by opts.N which is set to Ntrain in DNN experiments:
https://github.com/ChunyuanLI/pSGLD/blob/master/pSGLD_DNN/algorithms/SGLD_RMSprop.m#L51

Why is this the case? In the paper (https://arxiv.org/pdf/1512.07666v1.pdf) there is no such scaling.

I also checked SGLD_Adagrad.m and there is no scaling by Ntrain for the noise.

Hi Chunyuan,

Thanks for sharing. I found that in the 2-D simulation experiment the learning rate(injected Gaussian noise level) is kept constant, which doesn't satisfy the assumption 1 in your AAAI '16 paper. While in previous works e.g. Welling 2011, I found a polynomial decay scheme is applied. Will this be a problem?