# Non-Stationary Latent Bandits

arXiv: https://arxiv.org/abs/2012.00386 · HTML: https://mlsanity.com/paper/2012.00386/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models](https://mlsanity.com/paper/2108.06422/) (2021)
- [Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms](https://mlsanity.com/paper/2202.13001/) (2022)
- [Online learning in bandits with predicted context](https://mlsanity.com/paper/2307.13916/) (2023)
- [Non-Stationary Latent Auto-Regressive Bandits](https://mlsanity.com/paper/2402.03110/) (2024)
- [Information-Gathering in Latent Bandits](https://mlsanity.com/paper/2207.03635/) (2022)
- [Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting](https://mlsanity.com/paper/2410.01331/) (2024)
- [A Classification View on Meta Learning Bandits](https://mlsanity.com/paper/2504.04505/) (2025)
- [Beyond Random Noise: Insights on Anonymization Strategies from a Latent Bandit Study](https://mlsanity.com/paper/2310.00221/) (2023)
- [Designing an Interpretable Interface for Contextual Bandits](https://mlsanity.com/paper/2409.15143/) (2024)
- [Latent Preference Bandits](https://mlsanity.com/paper/2508.05367/) (2025)
- [A Direct Approach for Handling Contextual Bandits with Latent State Dynamics](https://mlsanity.com/paper/2604.08149/) (2026)
- [Latent Order Bandits](https://mlsanity.com/paper/2605.07304/) (2026)

## Abstract (arXiv)

Users of recommender systems often behave in a non-stationary fashion, due to their evolving preferences and tastes over time. In this work, we propose a practical approach for fast personalization to non-stationary users. The key idea is to frame this problem as a latent bandit, where the prototypical models of user behavior are learned offline and the latent state of the user is inferred online from its interactions with the models. We call this problem a non-stationary latent bandit. We propose Thompson sampling algorithms for regret minimization in non-stationary latent bandits, analyze them, and evaluate them on a real-world dataset. The main strength of our approach is that it can be combined with rich offline-learned models, which can be misspecified, and are subsequently fine-tuned online using posterior sampling. In this way, we naturally combine the strengths of offline and online learning.