中文
相关论文

相关论文: No-Regret is not enough! Bandits with General Cons…

200 篇论文

We address a generalization of the bandit with knapsacks problem, where a learner aims to maximize rewards while satisfying an arbitrary set of long-term constraints. Our goal is to design best-of-both-worlds algorithms that perform…

机器学习 · 计算机科学 2024-05-28 Martino Bernasconi , Matteo Castiglioni , Andrea Celli , Federico Fusco

The bandits with knapsack (BwK) framework models online decision-making problems in which an agent makes a sequence of decisions subject to resource consumption constraints. The traditional model assumes that each action consumes a…

机器学习 · 计算机科学 2023-06-16 Martino Bernasconi , Matteo Castiglioni , Andrea Celli , Federico Fusco

Bandits with Knapsacks (BwK) is a general model for multi-armed bandits under supply/budget constraints. While worst-case regret bounds for BwK are well-understood, we present three results that go beyond the worst-case perspective. First,…

机器学习 · 计算机科学 2021-12-30 Karthik Abinav Sankararaman , Aleksandrs Slivkins

Bandits with knapsacks (BwK) constitute a fundamental model that combines aspects of stochastic integer programming with online learning. Classical algorithms for BwK with a time horizon $T$ achieve a problem-independent regret bound of…

量子物理 · 物理学 2025-07-08 Yuexin Su , Ziyi Yang , Peiyuan Huang , Tongyang Li , Yinyu Ye

We consider Bandits with Knapsacks (henceforth, BwK), a general model for multi-armed bandits under supply/budget constraints. In particular, a bandit algorithm needs to solve a well-known knapsack problem: find an optimal packing of items…

数据结构与算法 · 计算机科学 2023-03-08 Nicole Immorlica , Karthik Abinav Sankararaman , Robert Schapire , Aleksandrs Slivkins

We investigate the contextual bandits with knapsack (CBwK) problem in a high-dimensional linear setting, where the feature dimension can be very large. Our goal is to harness sparsity to obtain sharper regret guarantees. To this end, we…

机器学习 · 计算机科学 2025-08-05 Wanteng Ma , Dong Xia , Jiashuo Jiang

The adversarial Bandit with Knapsack problem is a multi-armed bandits problem with budget constraints and adversarial rewards and costs. In each round, a learner selects an action to take and observes the reward and cost of the selected…

机器学习 · 计算机科学 2025-03-20 Mark Braverman , Jingyi Liu , Jieming Mao , Jon Schneider , Eric Xue

In this paper, we study the bandits with knapsacks (BwK) problem and develop a primal-dual based algorithm that achieves a problem-dependent logarithmic regret bound. The BwK problem extends the multi-arm bandit (MAB) problem to model the…

机器学习 · 计算机科学 2021-06-24 Xiaocheng Li , Chunlin Sun , Yinyu Ye

Bandits with Knapsacks (BwK), the generalization of the Bandits problem under global budget constraints, has received a lot of attention in recent years. Previous work has focused on one of the two extremes: Stochastic BwK where the rewards…

机器学习 · 计算机科学 2023-09-06 Giannis Fikioris , Éva Tardos

Bandits with knapsacks (BwK) is an influential model of sequential decision-making under uncertainty that incorporates resource consumption constraints. In each round, the decision-maker observes an outcome consisting of a reward and a…

机器学习 · 计算机科学 2022-09-27 Raunak Kumar , Robert Kleinberg

Multi-armed bandit problems are the predominant theoretical model of exploration-exploitation tradeoffs in learning, and they have countless applications ranging from medical trials, to communication networks, to Web search and advertising.…

数据结构与算法 · 计算机科学 2017-09-06 Ashwinkumar Badanidiyuru , Robert Kleinberg , Aleksandrs Slivkins

In this paper, we study the problem of bandits with knapsacks (BwK) in a non-stationary environment. The BwK problem generalizes the multi-arm bandit (MAB) problem to model the resource consumption associated with playing each arm. At each…

机器学习 · 计算机科学 2022-10-13 Shang Liu , Jiashuo Jiang , Xiaocheng Li

We unify two prominent lines of work on multi-armed bandits: bandits with knapsacks (BwK) and combinatorial semi-bandits. The former concerns limited "resources" consumed by the algorithm, e.g., limited supply in dynamic pricing. The latter…

机器学习 · 计算机科学 2018-02-22 Karthik Abinav Sankararaman , Aleksandrs Slivkins

Optimal regret bounds for Multi-Armed Bandit problems are now well documented. They can be classified into two categories based on the growth rate with respect to the time horizon $T$: (i) small, distribution-dependent, bounds of order of…

数据结构与算法 · 计算机科学 2017-04-12 Arthur Flajolet , Patrick Jaillet

We consider the problem of stochastic $K$-armed dueling bandit in the contextual setting, where at each round the learner is presented with a context set of $K$ items, each represented by a $d$-dimensional feature vector, and the goal of…

机器学习 · 计算机科学 2021-05-11 Aadirupa Saha , Aditya Gopalan

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

机器学习 · 计算机科学 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

We study an online setting, where a decision maker (DM) interacts with contextual bandit-with-knapsack (BwK) instances in repeated episodes. These episodes start with different resource amounts, and the contexts' probability distributions…

机器学习 · 计算机科学 2026-01-05 Wang Chi Cheung , Zitian Li

Fast changing states or volatile environments pose a significant challenge to online optimization, which needs to perform rapid adaptation under limited observation. In this paper, we give query and regret optimal bandit algorithms under…

机器学习 · 计算机科学 2024-01-18 Zhou Lu , Qiuyi Zhang , Xinyi Chen , Fred Zhang , David Woodruff , Elad Hazan

We propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge of the optimal regret, we only require that each base…

机器学习 · 计算机科学 2020-12-25 Aldo Pacchiano , Christoph Dann , Claudio Gentile , Peter Bartlett

We study dynamic regret minimization in unconstrained adversarial linear bandit problems. In this setting, a learner must minimize the cumulative loss relative to an arbitrary sequence of comparators…

机器学习 · 计算机科学 2026-03-30 Alberto Rumi , Andrew Jacobsen , Nicolò Cesa-Bianchi , Fabio Vitale
‹ 上一页 1 2 3 10 下一页 ›