# Multi-User Contextual Cascading Bandits for Personalized Recommendation

arXiv: https://arxiv.org/abs/2508.13981 · HTML: https://mlsanity.com/paper/2508.13981/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Improved Optimistic Algorithms for Logistic Bandits](https://mlsanity.com/paper/2002.07530/) (2020)
- [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)
- [Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning](https://mlsanity.com/paper/2107.01264/) (2021)
- [Improved Confidence Bounds for the Linear Logistic Model and Applications to Linear Bandits](https://mlsanity.com/paper/2011.11222/) (2020)
- [Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback](https://mlsanity.com/paper/2112.02856/) (2021)
- [Joint Value Estimation and Bidding in Repeated First-Price Auctions](https://mlsanity.com/paper/2502.17292/) (2025)
- [Assortment Optimization under Unknown MultiNomial Logit Choice Models](https://mlsanity.com/paper/1704.00108/) (2017)
- [Mitigating Exposure Bias in Online Learning to Rank Recommendation: A Novel Reward Model for Cascading Bandits](https://mlsanity.com/paper/2408.04332/) (2024)
- [Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits](https://mlsanity.com/paper/2503.00273/) (2025)

## Built on by (most cited first, 1 of 1)

- [Adaptive Quality-Diversity Trade-offs for Large-Scale Batch Recommendation](https://mlsanity.com/paper/2602.02024/) (2026)

## Abstract (arXiv)

We introduce a Multi-User Contextual Cascading Bandit model, a new combinatorial bandit framework that captures realistic online advertising scenarios where multiple users interact with sequentially displayed items simultaneously. Unlike classical contextual bandits, MCCB integrates three key structural elements: (i) cascading feedback based on sequential arm exposure, (ii) parallel context sessions enabling selective exploration, and (iii) heterogeneous arm-level rewards. We first propose Upper Confidence Bound with Backward Planning (UCBBP), a UCB-style algorithm tailored to this setting, and prove that it achieves a regret bound of widetildeO(√THN) over T episodes, H session steps, and N contexts per episode. Motivated by the fact that many users interact with the system simultaneously, we introduce a second algorithm, termed Active Upper Confidence Bound with Backward Planning (AUCBBP), which shows a strict efficiency improvement in context scaling, i.e., user scaling, with a regret bound of widetildeO(√T+HN). We validate our theoretical findings via numerical experiments, demonstrating the empirical effectiveness of both algorithms under various settings.