Losses and objectives · MLD-0877
Pareto frontier
Solutions for which no objective improves without worsening at least one other objective.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Compare model quality against inference cost.
Original caveat
A Pareto-optimal solution is not automatically the preferred one.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: ML · DL · SLM · LLM.
Aliases: None recorded.
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 ↗