The paper studies the trade‑off between maximizing rewards and accurately estimating current treatment effects in nonstationary multi‑armed bandits. For $K$‑armed bandits with H"older‑smooth mean rewards, the authors derive minimax bounds on expected dynamic regret under a high‑probability simultaneous coverage requirement for all current effects. They propose the TRACE algorithm, which achieves a regret–precision trade‑off that separates reward‑learning regret from the unavoidable cost of refreshing current‑effect estimates, and extend the method with an empirical‑Bernstein e‑process to adapt exploration while preserving worst‑case guarantees.
By Sharan Sahu, Martin T. Wells
The paper introduces DUCB-OGD, an algorithm that couples a Discounted Upper‑Confidence‑Bound sampler with Online Gradient Descent to address dynamic minimax regret in robust large‑language‑model post‑training. It operates under instantaneous mini‑batch‑only bandit feedback, tracking worst‑source performance without re‑evaluating historical data. Experiments on fine‑tuning, preference optimization, and reinforcement learning demonstrate that DUCB‑OGD improves worst‑group robustness with negligible computational overhead.
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. 09802v1 Announce Type: cross Abstract: 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.
By Udvas Das, Waris Radji, Debabrota Basu, Odalric-Ambrym Maillard
Exhaustively evaluating every candidate LLM configuration on every benchmark item to identify a high-performing one is costly. We formulate configuration selection as a cost-aware Bayesian bandit prob...
arXiv:2607. 09015v1 Announce Type: cross Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing.
By Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan
arXiv:2610.32910v1 Announce Type: new
Abstract: Regularised reinforcement learning (RL) algorithms rely on estimators, like Monte Carlo tree search or one-step look-ahead, to provide policy, value, o...
By Danilo Vucetic, Alexandre Larouche, Mohammad Pedramfar, Audrey Durand, Gauthier Gidel
arXiv:2502.14643v3 Announce Type: replace
Abstract: Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF),...
By Gengxu Li, Tingyu Xia, Yi Chang, Yuan Wu
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
By Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)
arXiv:2606. 01382v1 Announce Type: cross Abstract: Preference alignment is central to improving large language models, but standard reward-based formulations can be restrictive when human preferences are cyclic, non-transitive, or otherwise not representable by a scalar reward.
By Tianlong Nan, Xiaopeng Li, Christian Kroer, Tianyi Lin
arXiv:2609.25645v1 Announce Type: new
Abstract: Exhaustively evaluating every candidate LLM configuration on every benchmark item to identify a high-performing one is costly. We formulate configurati...
By Qian Xie, Yueli He, Nairen Cao
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.