search

torch / optim

A numeric optimization package for Torch.
Other
197 stars 152 forks source link

There is no L1 weightDecay in Torch. #120

Open amirkhango opened 8 years ago

amirkhango commented 8 years ago

The weightDecay in Torch refers to L2, Yes? So How can I implemment L1 weightDecay?

Kaixhin commented 8 years ago

Example code for L1 and L2 weight decay (which is added manually in the training loop) can be found here.