Losses and objectives · MLD-0390
Expected risk
Expected loss over the target data distribution.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Reason about average future prediction error.
Original caveat
The true distribution is usually unknown.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: ML · DL · SLM · LLM.
Aliases: Population risk.
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 ↗