Supplemental practical concepts · MLD-0738
Minimax optimization
Optimizing one set of choices against the worst or maximizing response of another set.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Express adversarial training as an inner maximization and outer minimization.
Original caveat
General minimax problems need not converge under simple alternating updates.
Context and aliases
Level: Advanced. Stages: Training · Inference · Evaluation.
Tags: ML · DL · LLM · SLM.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- Transformers glossary ↗ · Consulted
- OpenAI Spinning Up: reinforcement learning ↗ · Consulted
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗