Skip to content

[Fix] Poor performance with the NegativeBinomial DistributionLoss #1289

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
marcopeix merged 1 commit into from
Mar 18, 2025
Merged

[Fix] Poor performance with the NegativeBinomial DistributionLoss #1289

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions nbs/losses.pytorch.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1454,8 +1454,8 @@
" mu = F.softplus(mu) + 1e-8\n",
" alpha = F.softplus(alpha) + 1e-8 # alpha = 1/total_counts\n",
" if (loc is not None) and (scale is not None):\n",
" mu *= loc\n",
" alpha /= (loc + 1.)\n",
" mu = mu * scale + loc\n",
" alpha /= (scale + 1.)\n",
"\n",
" # mu = total_count * (probs/(1-probs))\n",
" # => probs = mu / (total_count + mu)\n",
Expand Down
4 changes: 2 additions & 2 deletions neuralforecast/losses/pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -857,8 +857,8 @@ def nbinomial_scale_decouple(output, loc=None, scale=None):
mu = F.softplus(mu) + 1e-8
alpha = F.softplus(alpha) + 1e-8 # alpha = 1/total_counts
if (loc is not None) and (scale is not None):
mu *= loc
alpha /= loc + 1.0
mu = mu * scale + loc
alpha /= scale + 1.0

# mu = total_count * (probs/(1-probs))
# => probs = mu / (total_count + mu)
Expand Down