# Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation

arXiv: https://arxiv.org/abs/2609.37800 · HTML: https://mlsanity.com/paper/2609.37800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 46 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [An Information-Theoretic Analysis of Thompson Sampling](https://mlsanity.com/paper/1403.5341/) (2014)
- [Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing](https://mlsanity.com/paper/2002.07033/) (2020)
- [Rotting Bandits](https://mlsanity.com/paper/1702.07274/) (2017)
- [Hierarchical Bayesian Bandits](https://mlsanity.com/paper/2111.06929/) (2021)
- [Batched Thompson Sampling](https://mlsanity.com/paper/2110.00202/) (2021)
- [Fast Distributed Bandits for Online Recommendation Systems](https://mlsanity.com/paper/2007.08061/) (2020)
- [Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation](https://mlsanity.com/paper/2008.09368/) (2020)
- [MobileRec: A Large-Scale Dataset for Mobile Apps Recommendation](https://mlsanity.com/paper/2303.06588/) (2023)
- [Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Sampling](https://mlsanity.com/paper/2104.15046/) (2021)
- [Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendation](https://mlsanity.com/paper/2208.11926/) (2022)

## Abstract (arXiv)

Many recommender services repeatedly encounter cold-start cohorts, where new users arrive with little or no interaction history. This creates two challenges: learning user preferences quickly from limited feedback and sustaining useful recommendations when each user has a finite catalog that can become repetitive or depleted over time. We propose CohortMix-TS, a warm-started mixture bandit that learns latent user groups from earlier cohorts and uses available metadata to construct group-informed priors for new users. Starting from these fixed priors, the model personalizes independently as feedback from each user becomes available. Session slates combine Thompson sampling with diversity and inventory-depletion controls. We evaluate CohortMix-TS through simulation, semi-synthetic experiments, and a 25-day randomized in-the-wild deployment with 713 registered participants in a Campus Games quiz application. Our evaluations show that cross-cohort transfer improves early recommendation quality and user-level regret, while inventory-aware slate construction helps prevent premature exhaustion of preferred items. In the field deployment, treatment users also showed a larger early-to-late change in correctness than users receiving random recommendations. Together, these results show how warm-start transfer and inventory-aware recommendations can support personalization for short-lived, repeatedly cold-starting cohorts.