Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles.
Zhiwei TangDmitry RybinTsung-Hui ChangPublished in: CoRR (2023)
Keyphrases
- learning process
- learning algorithm
- knowledge acquisition
- language acquisition
- active learning
- prior knowledge
- mobile learning
- optimization problems
- online learning
- learning systems
- learning tasks
- learning problems
- global optimization
- creative problem solving
- e learning
- inductive inference
- user feedback
- neural network
- search engine
- support vector