arXiv:2607.00155v1 Announce Type: new Abstract: We study runtime human oversight of an AI agent when private information runs in both directions: the human privately knows her reward function, while the AI privately knows the quality of the action it proposes. This is the kind of…
arXiv:2312.15427v3 Announce Type: replace Abstract: Stochastic optimization is a widely used approach for optimization under uncertainty, where uncertain input parameters are modeled by random variables. Exact or approximation algorithms have been obtained for several fundamental…
arXiv cs.LG
TIER_1English(EN)·Bin Du, Chang Liu, Dingqi Zhu, Lintao Ye, Dengfeng Sun·
arXiv:2607.00680v1 Announce Type: new Abstract: We study distributed online submodular maximization under partition matroid constraints, in which multiple agents select a limited number of actions from their own subsets sequentially to maximize the cumulative value of a sequence …
We study distributed online submodular maximization under partition matroid constraints, in which multiple agents select a limited number of actions from their own subsets sequentially to maximize the cumulative value of a sequence of objective functions. We develop a unified alg…
arXiv:2606.31449v1 Announce Type: new Abstract: We investigate the contextual slate bandit problem with generalized linear rewards under limited adaptivity. At each round, the learner is presented with $N$ sets of items, where each item is represented by a $d$-dimensional feature…
arXiv cs.LG
TIER_1English(EN)·Steve Hanneke, Kun Wang·
arXiv:2605.09200v2 Announce Type: replace Abstract: We study adversarial noisy bandits given a known function class $\mathcal{F}$. In each round, the adversary selects a function $f \in \mathcal{F}$, the learner chooses an arm, and then observes a noisy reward determined by the c…
We investigate the contextual slate bandit problem with generalized linear rewards under limited adaptivity. At each round, the learner is presented with $N$ sets of items, where each item is represented by a $d$-dimensional feature vector. The learner then constructs a slate by …
arXiv:2606.28616v1 Announce Type: new Abstract: In stochastic linear bandits, the canonical Upper Confidence Bound (UCB) algorithm admits a simple frequentist regret analysis but can be computationally demanding, while Thompson Sampling (TS) is computationally attractive yet typi…
arXiv cs.LG
TIER_1English(EN)·Ahmed Sayeed Faruk, Mohammad Shahverdikondori, Elena Zheleva·
arXiv:2510.19119v2 Announce Type: replace Abstract: In networked environments, it is common for users to share recommendations about content, products, services, and possible courses of action. Whether these recommendations are accepted and acted upon is highly context-dependent,…
arXiv cs.LG
TIER_1English(EN)·Thomas Hira, Victor Boone, Urtzi Ayesta, Ina Maria Verloop·
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. The focus is restricted to a ``pure'' regret benchmark, that compares the …
In many online learning and bandit problems, the actions we consider possess inherent similarities--for instance because they share latent traits, tags, or hierarchical structure. We study online learning with a similarity-structured action set, encoded by a rooted tree whose lea…
arXiv stat.ML
TIER_1English(EN)·Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli·
arXiv:2409.05980v2 Announce Type: replace Abstract: Rested and Restless Bandits are two well-known bandit settings that are useful to model real-world sequential decision-making problems in which the expected reward of an arm evolves over time due to the actions we perform or due…
arXiv:2605.09454v2 Announce Type: replace Abstract: We study the $\textit{single-index bandit}$ problem, where rewards depend on an unknown one-dimensional projection of high-dimensional contexts through an unknown reward function. This model extends linear and generalized linear…
arXiv stat.ML
TIER_1English(EN)·Lucas L\'evy, Jean-Lou Valeau, Arya Akhavan, Patrick Rebeschini·
arXiv:2510.24187v3 Announce Type: replace Abstract: We consider the adversarial linear bandits setting and present a unified algorithmic framework that bridges Follow-the-Regularized-Leader (FTRL) and Follow-the-Perturbed-Leader (FTPL) methods, extending the known connection betw…
arXiv stat.ML
TIER_1English(EN)·Francisco N. F. Q. Simoes, Itai Feigenbaum, Mehdi Dastani, Thijs van Ommen·
arXiv:2502.06577v3 Announce Type: replace-cross Abstract: Causal knowledge can be used to support decision-making problems. This has been recognized in the causal bandits literature, where a causal (multi-armed) bandit is characterized by a causal graphical model and a target var…
