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.
arXiv:2607. 23679v1 Announce Type: new Abstract: Recent years have witnessed increasing interests in tackling heteroscedastic noise in bandits and reinforcement learning.
By Heyang Zhao, Tianyuan Jin, Weixin Wang, Vincent Y. F. Tan, Pan Xu, Quanquan Gu
arXiv:2607. 02891v1 Announce Type: new Abstract: Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can change over time, while user preferences, demand curves, and patient responses may evolve.
By Zihao Hu, Yuan Yao, Jiheng Zhang, Zhengyuan Zhou
The paper extends the idea that contexts are cheap for linear bandits from i.i.d. settings to Markovian context processes. By assuming uniform geometric ergodicity, the authors construct a stationary surrogate action set and use a delayed‑update scheme to mitigate bias from nonstationary conditional context distributions. They provide a phased algorithm for unknown stationary distributions and achieve high‑probability regret bounds comparable to standard linear bandit oracles in fast‑mixing regimes, with empirical validation showing gains over LinUCB.
By Kaan Buyukkalayci, Osama Hanna, Christina Fragouli
arXiv:2606. 00984v1 Announce Type: cross Abstract: We study linear contextual bandits under rare parameter updates: the learner may incorporate reward feedback into its parameter estimate only at a small number of update times, while still observing contexts online and selecting actions sequentially.
By Sanghoon Yu, Min-hwan Oh
The paper introduces Online Hyperparameter Optimization (OHPO), framing it as an infinitely many‑armed bandit problem over mixed and conditional search spaces. It proposes the IMABO framework, which couples any bandit policy with any oracle for proposing new configurations, and presents IMOSS—a restart‑free anytime policy with provable regret bounds. Experiments show that IMABO, combined with practical oracles such as TPE, an incumbent‑mutation oracle, and a pretrained tabular foundation model, outperforms random search across a range of settings from classical ML models to LLM‑based agents.
By Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine
arXiv:2606. 27448v1 Announce Type: new Abstract: This paper studies the problem of regret minimization in Markovian bandits with \emph{non-observable states} and possibly \emph{constrained} decision epochs.
By Thomas Hira, Victor Boone, Urtzi Ayesta, Ina Maria Verloop
arXiv:2602. 09456v2 Announce Type: replace Abstract: We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression.
By Hao Qin, Chicheng Zhang
The paper introduces a new approach to safety in contextual bandits with continuous actions, focusing on high‑probability constraints on the realized cost rather than expected cost. It presents the High‑Probability Constrained UCB algorithm, which balances reward exploration with conservative safety estimation, and provides theoretical regret guarantees for linear models and extensions to general function classes. Experiments demonstrate that this realized‑cost safety framework significantly reduces safety violations compared to expected‑cost constrained methods.
By Spyros Dragazis, Aldo Pacchiano
arXiv:2510. 07424v3 Announce Type: replace Abstract: We study linear contextual bandits with paid observations, where at each round the learner observes a context, selects an action, and may pay a fixed cost to observe feedback from a subset of arms.
By Nathan Boyer, Dorian Baudry, Patrick Rebeschini
arXiv:2605.20854v3 Announce Type: replace
Abstract: We provide the first regret analysis of ReMax in stochastic multi-armed bandits. Originally introduced for reinforcement learning, ReMax is motivat...
By Bingkui Tong, Junpei Komiyama, Soichiro Nishimori, Paavo Parmas
arXiv:2510.10730v3 Announce Type: replace
Abstract: We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two mo...
By Jiazheng Sun, Weixin Wang, Pan Xu