对比五种UCB算法在自适应神经网络中的表现，优化边缘计算的准确率与能耗平衡。
A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks
- 引入四种新UCB算法，动态调节推理路径以平衡精度与开销。
- UCB-V和UCB-Tuned在准确率-延迟、准确率-能耗权衡上表现最优。
- 实验验证所有算法均实现次线性累积遗憾，UCB-Bayes收敛最快。
边缘计算环境对能耗和延迟有严格限制，使得深度神经网络部署面临挑战。因此，在边缘场景中，能够动态平衡计算成本或延迟与预测准确率的智能自适应推理策略至关重要。本文基于采用多臂赌博机（MAB）框架的自适应深度神经网络（ADNNs），在现有文献使用UCB1策略动态选择置信阈值以实现高效提前退出的基础上，首次系统比较了四种新增的UCB策略：UCB-V、UCB-Tuned、UCB-Bayes和UCB-BwK，评估其在准确率、能耗与延迟之间的权衡表现。所提策略应用于ResNet与MobileViT模型，并在CIFAR-10、CIFAR-10.1和CIFAR-100基准数据集上进行测试。实验结果表明，所有策略均实现次线性累积遗憾，其中UCB-Bayes收敛最快，其次为UCB-Tuned和UCB-V；最终，UCB-V与UCB-Tuned在准确率-延迟与准确率-能耗的帕累托前沿上占据主导地位。代码已公开于：https://github.com/gr3gor1/MAB_UCB
原文摘要 · Abstract (English)
Edge computing environments impose strict constraints on energy consumption and latency, making the deployment of deep neural networks a significant challenge. Therefore, smart and adaptive inference strategies that dynamically balance computational cost or latency with predictive accuracy are critical in edge computing scenarios. In this work, we build on Adaptive Deep Neural Networks (ADNNs) that employ the Multi-Armed Bandit (MAB) framework. Current literature leverages the first version of the Upper Confidence Bound (UCB1) strategy to dynamically select the optimal confidence threshold, enabling efficient early exits without sacrificing accuracy. However, we introduce four additional Upper Confidence Bound strategies in ADNNs, namely UCB-V, UCB-Tuned, UCB-Bayes, and UCB-BwK, and perform, for the first time, a comparative study of these strategies with respect to trade-offs between accuracy, energy consumption, and latency. The proposed UCB strategies are employed on the ResNet and MobileViT neural networks, and are evaluated on the benchmark datasets of CIFAR-10, CIFAR-10.1, and CIFAR-100. Experimental results demonstrate that all strategies achieve sub-linear cumulative regret, with UCB-Bayes converging the fastest, followed by UCB-Tuned and UCB-V. Finally, UCB-V and UCB-Tuned dominate the Pareto Frontiers of accuracy-latency and accuracy-energy trade-offs. The implementation code is available here: https://github.com/gr3gor1/MAB_UCB
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。