RASP-Tuner
Cross-source consensus on RASP-Tuner from 1 sources and 5 claims.
1 sources · 5 claims
Uses
How it works
Evidence quality
Highlighted claims
- RASP-Tuner targets online context-conditioned regret minimization in non-stationary black-box optimization. — RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
- RASP-Tuner is intended to help when context is informative about the latent environment and can add harmful variance when context is irrelevant. — RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
- RASP-Tuner is positioned for non-stationary settings with recurring operational contexts that predict the active optimum. — RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
- Candidate generation blends the current parameter with a retrieved historical hint before scoring candidates. — RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
- RASP-Tuner combines retrieval, historical parameter hints, soft prompts, a mixture-of-experts surrogate, and lower-confidence-bound candidate selection. — RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments