提出可自适应选择模型的级联强化学习方法，提升边缘推理效率。
Cascading Bandits With Feedback
- 基于反馈动态调整模型选择顺序，实现持续优化
- 下置信界与汤普森采样达到常数级后悔值
- 适合资源受限场景下的智能模型调度
针对边缘推理中的挑战，研究一种级联老虎机模型变体，其中每个臂对应一个具有准确率和错误概率的推理模型。分析了四种决策策略——探索后确定、动作消除、下置信界（LCB）和汤普森采样，并为每种策略提供了精确的理论后悔界限。与经典老虎机设置不同，探索后确定和动作消除因在探索阶段后固定顺序，导致后悔值次优，难以适应变化；而LCB和汤普森采样通过持续利用观测反馈更新决策，实现了常数阶O(1)后悔。仿真结果验证了理论发现，凸显了在不确定性环境下自适应决策对高效边缘推理的关键作用。
原文摘要 · Abstract (English)
Motivated by the challenges of edge inference, we study a variant of the cascade bandit model in which each arm corresponds to an inference model with an associated accuracy and error probability. We analyse four decision-making policies-Explore-then-Commit, Action Elimination, Lower Confidence Bound (LCB), and Thompson Sampling-and provide sharp theoretical regret guarantees for each. Unlike in classical bandit settings, Explore-then-Commit and Action Elimination incur suboptimal regret because they commit to a fixed ordering after the exploration phase, limiting their ability to adapt. In contrast, LCB and Thompson Sampling continuously update their decisions based on observed feedback, achieving constant O(1) regret. Simulations corroborate these theoretical findings, highlighting the crucial role of adaptivity for efficient edge inference under uncertainty.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。