Raymond-Xue

Results 5 comments of Raymond-Xue

> The first thing to establish is whether your l2_norm_clip and noise_multiplier are appropriately set. As a sanity check, try setting l2_norm_clip very large (1e3) and noise multiplier very small...

> l2_clip_norm is completely model specific. If it is too low, your gradients will be clipped heavily, incurring bias. If it is too high, a huge amount of noise will...

Hi, have you solve this problem? I am trying to reproduce this paper these days, too.