English
Related papers

Related papers: Covert Online Decision Making: From Sequential Hyp…

200 papers

This study investigates general model-based incident handler's asymptotic behaviors in time against cyber attacks to control systems. The attacker's and the defender's dynamic decision making is modeled as an equilibrium of a dynamic…

Systems and Control · Electrical Eng. & Systems 2021-03-25 Hampei Sasahara , Henrik Sandberg

We investigate the problem dependent regime in the stochastic Thresholding Bandit problem (TBP) under several shape constraints. In the TBP, the objective of the learner is to output, at the end of a sequential game, the set of arms whose…

Machine Learning · Statistics 2021-06-21 James Cheshire , Pierre Ménard , Alexandra Carpentier

Many interventions, such as vaccines in clinical trials or coupons in online marketplaces, must be assigned sequentially without full knowledge of their effects. Multi-armed bandit algorithms have proven successful in such settings.…

Machine Learning · Statistics 2026-05-07 Aidan Gleich , Eric Laber , Alexander Volfovsky

Many cybersecurity problems that require real-time decision-making based on temporal observations can be abstracted as a sequence modeling problem, e.g., network intrusion detection from a sequence of arriving packets. Existing approaches…

Cryptography and Security · Computer Science 2023-12-19 Jingdi Chen , Hanhan Zhou , Yongsheng Mei , Gina Adam , Nathaniel D. Bastian , Tian Lan

Personalization is a crucial aspect of many online experiences. In particular, content ranking is often a key component in delivering sophisticated personalization results. Commonly, supervised learning-to-rank methods are applied, which…

Machine Learning · Computer Science 2020-04-29 Beyza Ermis , Patrick Ernst , Yannik Stein , Giovanni Zappella

Algorithm selection is typically based on models of algorithm performance, learned during a separate offline training sequence, which can be prohibitively expensive. In recent work, we adopted an online approach, in which a performance…

Artificial Intelligence · Computer Science 2013-01-31 Matteo Gagliolo , Juergen Schmidhuber

Users of recommender systems often behave in a non-stationary fashion, due to their evolving preferences and tastes over time. In this work, we propose a practical approach for fast personalization to non-stationary users. The key idea is…

Machine Learning · Computer Science 2020-12-02 Joey Hong , Branislav Kveton , Manzil Zaheer , Yinlam Chow , Amr Ahmed , Mohammad Ghavamzadeh , Craig Boutilier

In this paper we study the online learning problem involving rested and restless multiarmed bandits with multiple plays. The system consists of a single player/user and a set of K finite-state discrete-time Markov chains (arms) with unknown…

Optimization and Control · Mathematics 2015-03-25 Cem Tekin , Mingyan Liu

We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii)…

Machine Learning · Computer Science 2023-03-21 Siyu Chen , Yitan Wang , Zhaoran Wang , Zhuoran Yang

We study the problem of repeated two-sided matching with uncertain preferences (two-sided bandits), and no explicit communication between agents. Recent work has developed algorithms that converge to stable matchings when one side (the…

Multiagent Systems · Computer Science 2025-08-13 Gaurab Pokharel , Sanmay Das

We study a recommender system for quantum data using the linear contextual bandit framework. In each round, a learner receives an observable (the context) and has to recommend from a finite set of unknown quantum states (the actions) which…

Quantum Physics · Physics 2025-10-28 Shrigyan Brahmachari , Josep Lumbreras , Marco Tomamichel

We consider an online strategic classification problem where each arriving agent can manipulate their true feature vector to obtain a positive predicted label, while incurring a cost that depends on the amount of manipulation. The learner…

Machine Learning · Computer Science 2024-03-28 Lingqing Shen , Nam Ho-Nguyen , Khanh-Hung Giang-Tran , Fatma Kılınç-Karzan

We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random covariate. The goal is to maximize cumulative expected reward.…

Statistics Theory · Mathematics 2010-03-09 Philippe Rigollet , Assaf Zeevi

This paper studies the deception applied on agent in a partially observable Markov decision process. We introduce deceptive kernel function (the kernel) applied to agent's observations in a discrete POMDP. Based on value iteration, value…

Artificial Intelligence · Computer Science 2020-08-14 Zhili Zhang , Quanyan Zhu

This paper identifies and addresses dynamic selection problems in online learning algorithms with endogenous data. In a contextual multi-armed bandit model, a novel bias (self-fulfilling bias) arises because the endogeneity of the data…

Econometrics · Economics 2023-09-29 Jin Li , Ye Luo , Xiaowei Zhang

The nodes' interconnections on a social network often reflect their dependencies and information-sharing behaviors. Nevertheless, abnormal nodes, which significantly deviate from most of the network concerning patterns or behaviors, can…

Multiagent Systems · Computer Science 2025-08-28 Xiaotong Cheng , Setareh Maghsudi

This work investigates the problem of analyzing privacy of abrupt changes for general Markov processes. These processes may be affected by changes, or exogenous signals, that need to remain private. Privacy refers to the disclosure of…

Systems and Control · Electrical Eng. & Systems 2021-10-04 Alessio Russo , Alexandre Proutiere

In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions. Our goal is to identify the $K$ arms with the largest means with high confidence, by drawing samples from the…

Machine Learning · Computer Science 2017-05-22 Haotian Jiang , Jian Li , Mingda Qiao

We present a new algorithm based on an gradient ascent for a general Active Exploration bandit problem in the fixed confidence setting. This problem encompasses several well studied problems such that the Best Arm Identification or…

Machine Learning · Statistics 2019-05-21 Pierre Ménard

In stochastic contextual bandits, an agent sequentially makes actions from a time-dependent action set based on past experience to minimize the cumulative regret. Like many other machine learning algorithms, the performance of bandits…

Machine Learning · Computer Science 2024-04-09 Yue Kang , Cho-Jui Hsieh , Thomas C. M. Lee
‹ Prev 1 8 9 10 Next ›