A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks
cs.LG, cs.AI
Submitted: 2026-04-27
Updated: 2026-05-22
Comments: The paper has been accepted for publication in IEEE SMARTCOMP 2026
Journal ref: 2026 IEEE International Conference on Smart Computing (SmartComp)
DOI: 10.1109/SmartComp69968.2026.00018
License: http://creativecommons.org/licenses/by/4.0/
The gist: Edge computing environments impose strict constraints on energy consumption and latency, making the deployment of deep neural networks a significant challenge.
Terminology
Abstract
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
Sources
- Mixtral of Experts
- Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
- Unsupervised Early Exit in DNNs with Multiple Exits
- DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
- MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
- Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks