# Cascading Bandits With Feedback

arXiv: https://arxiv.org/abs/2511.10938 · HTML: https://mlsanity.com/paper/2511.10938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Thompson Sampling for Combinatorial Semi-Bandits](https://mlsanity.com/paper/1803.04623/) (2018)
- [Cascading Bandits: Learning to Rank in the Cascade Model](https://mlsanity.com/paper/1502.02763/) (2015)
- [Cascading Bandits for Large-Scale Recommendation Problems](https://mlsanity.com/paper/1603.05359/) (2016)
- [Thompson Sampling Algorithms for Cascading Bandits](https://mlsanity.com/paper/1810.01187/) (2018)
- [Cost-aware Cascading Bandits](https://mlsanity.com/paper/1805.08638/) (2018)
- [Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting](https://mlsanity.com/paper/2001.08655/) (2020)

## Abstract (arXiv)

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.