New research explores advanced multi-armed bandit algorithms · 8 sources tracked
ByPulseAugur Editorial·[15 sources]·
This cluster features several research papers exploring advancements in multi-armed bandit algorithms. Topics include characterizing learnability in adversarial noisy bandits, developing contextual slate bandits with limited adaptivity, and proposing new exploration strategies for linear bandits. Additionally, research is presented on learning peer influence probabilities, handling non-observable states in Markovian bandits, and optimizing conditional causal bandits.
AI
IMPACT
These theoretical advancements in bandit algorithms could lead to more efficient and effective decision-making systems in various AI applications.
RANK_REASON
Cluster consists of multiple academic papers on theoretical aspects of bandit algorithms.
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…
