[Paper] Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts
Source: arXiv - 2606.09802v1
Overview
We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, each having its personalized preference vector, and in the presence of context distributions that are drifting over time. Under practitioner-friendly assumptions, we reduce this setting to linear bandit with stationary mean but heteroskedastic and non-stationary noise. We further study the case when the learner must ensure the mean reward of each decision must exceed that of a baseline strategy $\boldsymbolπ_0$ at each decision step. We introduce Dri-MED, an algorithm inspired from the linear version of the MED strategy, and carefully adapted to handle the non-stationary heteroskedastic noise. We show that the instance-dependent regret scales as $\tilde{\mathcal O}\left(\fracκ{\tildeΔ}d^2(\log(T)\right)$, where $\tildeΔ$ is the constraint-aware sub-optimality gap subject to policy $π_0$, with variance-aware multiplicative term $κ$ that we carefully handle using heteroskedastic regression. We further show Dri-MED enjoys $\tilde{\mathcal{O}}(d)$ expected constraint violations. Our numerical results suggest that Dri-MED significantly outperforms conservative baselines that ignores the drift and preference structure.
Key Contributions
This paper presents research in the following areas:
- cs.LG
- cs.AI
- stat.ML
Methodology
Please refer to the full paper for detailed methodology.
Practical Implications
This research contributes to the advancement of cs.LG.
Authors
- Udvas Das
- Waris Radji
- Debabrota Basu
- Odalric-Ambrym Maillard
Paper Information
- arXiv ID: 2606.09802v1
- Categories: cs.LG, cs.AI, stat.ML
- Published: June 8, 2026
- PDF: Download PDF