English
Related papers

Related papers: Tractable Multinomial Logit Contextual Bandits wit…

200 papers

Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large language models (LLMs). Despite its empirical advantage, the…

Machine Learning · Computer Science 2026-03-12 Heyang Zhao , Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

The contextual duelling bandit problem models adaptive recommender systems, where the algorithm presents a set of items to the user, and the user's choice reveals their preference. This setup is well suited for implicit choices users make…

Machine Learning · Computer Science 2025-08-27 Suryanarayana Sankagiri , Jalal Etesami , Pouria Fatemi , Matthias Grossglauser

We consider the adversarial linear contextual bandit setting, which allows for the loss functions associated with each of $K$ arms to change over time without restriction. Assuming the $d$-dimensional contexts are drawn from a fixed known…

Machine Learning · Computer Science 2023-05-25 Julia Olkhovskaya , Jack Mayo , Tim van Erven , Gergely Neu , Chen-Yu Wei

Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at…

Machine Learning · Statistics 2017-03-07 Abbas Kazerouni , Mohammad Ghavamzadeh , Yasin Abbasi-Yadkori , Benjamin Van Roy

We study the performance guarantees of exploration-free greedy algorithms for the linear contextual bandit problem. We introduce a novel condition, named the \textit{Local Anti-Concentration} (LAC) condition, which enables a greedy bandit…

Machine Learning · Statistics 2025-01-17 Seok-Jin Kim , Min-hwan Oh

We study the stochastic bandit problem with ReLU neural network structure. We show that a $\tilde{O}(\sqrt{T})$ regret guarantee is achievable by considering bandits with one-layer ReLU neural networks; to the best of our knowledge, our…

Machine Learning · Computer Science 2024-05-14 Kan Xu , Hamsa Bastani , Surbhi Goel , Osbert Bastani

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…

Machine Learning · Computer Science 2025-08-05 Wanteng Ma , Dong Xia , Jiashuo Jiang

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult…

Machine Learning · Computer Science 2018-12-18 Maria Dimakopoulou , Zhengyuan Zhou , Susan Athey , Guido Imbens

The generalized linear bandit framework has attracted a lot of attention in recent years by extending the well-understood linear setting and allowing to model richer reward structures. It notably covers the logistic model, widely used when…

Machine Learning · Computer Science 2020-06-09 Louis Faury , Marc Abeille , Clément Calauzènes , Olivier Fercoq

We study the problem of representation learning in stochastic contextual linear bandits. While the primary concern in this domain is usually to find realizable representations (i.e., those that allow predicting the reward function at any…

Machine Learning · Computer Science 2022-10-25 Andrea Tirinzoni , Matteo Papini , Ahmed Touati , Alessandro Lazaric , Matteo Pirotta

This paper investigates the problem of non-stationary linear bandits, where the unknown regression parameter is evolving over time. Existing studies develop various algorithms and show that they enjoy an…

Machine Learning · Computer Science 2021-12-23 Peng Zhao , Lijun Zhang , Yuan Jiang , Zhi-Hua Zhou

Model selection in supervised learning provides costless guarantees as if the model that best balances bias and variance was known a priori. We study the feasibility of similar guarantees for cumulative regret minimization in the stochastic…

Machine Learning · Computer Science 2023-10-25 Sanath Kumar Krishnamurthy , Adrienne Margaret Propp , Susan Athey

We propose the first regret-based approach to the Graphical Bilinear Bandits problem, where $n$ agents in a graph play a stochastic bilinear bandit game with each of their neighbors. This setting reveals a combinatorial NP-hard problem that…

Machine Learning · Computer Science 2022-10-13 Geovani Rizk , Igor Colin , Albert Thomas , Rida Laraki , Yann Chevaleyre

In online exploration systems where users with fixed preferences repeatedly arrive, it has recently been shown that O(1), i.e., bounded regret, can be achieved when the system is modeled as a linear contextual bandit. This result may be of…

Machine Learning · Computer Science 2023-07-03 Enoch Hyunwook Kang , P. R. Kumar

Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the stochastic contextual bandit problem with general bounded reward…

Machine Learning · Computer Science 2022-05-31 Yu-Heng Hung , Ping-Chun Hsieh

We introduce a new stochastic smoothing perspective to study adversarial contextual bandit problems. We propose a general algorithm template that represents random perturbation based algorithms and identify several perturbation…

Machine Learning · Statistics 2019-06-12 Young Hun Jung , Ambuj Tewari

We study linear contextual bandits with access to a large, confounded, offline dataset that was sampled from some fixed policy. We show that this problem is closely related to a variant of the bandit problem with side information. We…

Machine Learning · Computer Science 2021-08-11 Guy Tennenholtz , Uri Shalit , Shie Mannor , Yonathan Efroni

Online linear programming plays an important role in both revenue management and resource allocation, and recent research has focused on developing efficient first-order online learning algorithms. Despite the empirical success of…

Machine Learning · Statistics 2025-01-07 Wenzhi Gao , Dongdong Ge , Chenyu Xue , Chunlin Sun , Yinyu Ye

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite.…

Machine Learning · Computer Science 2012-02-15 Nicolò Cesa-Bianchi , Sham Kakade

We study the adaptive control of an unknown linear system with a quadratic cost function subject to safety constraints on both the states and actions. The challenges of this problem arise from the tension among safety, exploration,…

Systems and Control · Electrical Eng. & Systems 2021-11-02 Yingying Li , Subhro Das , Jeff Shamma , Na Li