Losses and objectives · MLD-0524
Huber loss
A loss that is quadratic near zero error and linear beyond a threshold.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Fit regression with moderate resistance to outliers.
Original caveat
Huber and smooth-L1 implementations can differ by scaling.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: ML · DL · SLM · LLM.
Aliases: Smooth L1 variant.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- scikit-learn: evaluation metrics ↗ · Reference link
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗