Cascading Bandits With Feedback

2025-11-14

AI Summary

This paper addresses the cascaded inference decision problem in edge intelligence scenarios, where the objective is to dynamically balance model accuracy and error probability across multiple models to minimize cumulative regret. We formulate each “arm” as an inference model characterized by its accuracy and error probability, embedded within a cascaded feedback structure. To this end, we propose an adaptive online learning–based decision framework. Theoretically, we prove that both the Lower Confidence Bound (LCB) and Thompson Sampling strategies achieve *O*(1) constant regret—substantially outperforming static or phased strategies such as Explore-then-Commit and Action Elimination. Our analysis further reveals that adaptive confidence updating is critical for overcoming the limitations of fixed-order execution. Extensive simulations validate the framework’s efficiency and robustness under uncertain edge environments.

Technology Category

• Machine Learning: Online Learning & Bandits
• Reasoning under Uncertainty: Sequential Decision Making
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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.

Problem

• Optimizing model selection for edge inference under uncertainty
• Analyzing adaptive decision policies to minimize regret in cascading bandits
• Evaluating bandit algorithms for accuracy-error tradeoffs in edge computing

Innovation

• Cascade bandit model for edge inference optimization
• LCB and Thompson Sampling achieve constant regret
• Continuous decision updates based on observed feedback