NegativeBinomialLikelihood - Invalid values during training

Description

Contributor guide

Tech stack

pythonpytorch

Domain

machine learningdata

Issue type

bug

DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.

3

Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.

1-3 hours

Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.

stale

ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.

needs investigation

Prerequisites

Basic understanding of probabilistic modelsFamiliarity with PyTorch

Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.

20

Research direction

Investigate the NegativeBinomialLikelihood class in the darts codebase, likely in darts/models/likelihood.py or similar. The issue states that parameters assume invalid values during training, so check for parameter constraints (e.g., variance greater than mean) and ensure proper initialization or clamping. Look at the training loop for any gradient issues or unbounded parameter updates. Since there are no comments or PRs, a good starting point is to reproduce the error with a minimal example and trace the parameter values.