adaptive learning
Adaptive learning refers to methods where the learning rate or model parameters adjust dynamically based on the performance of the model during training, improving convergence and efficiency.
- AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
- AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
- Explaining the Law of Supply and Demand via Online Learning
- Knowledge Starts with Practice: Knowledge-Aware Exercise Generative Recommendation with Adaptive Multi-Agent Cooperation
- Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
- Transformers are almost optimal metalearners for linear classification