English
Related papers

Related papers: Towards minimax optimal algorithms for Active Simp…

200 papers

Model checking of strategic ability under imperfect information is known to be hard. The complexity results range from NP-completeness to undecidability, depending on the precise setup of the problem. No less importantly, fixpoint…

Multiagent Systems · Computer Science 2017-03-14 Wojciech Jamroga , Michał Knapik , Damian Kurpiewski

We introduce the model selection problem in pure exploration linear bandits, where the learner needs to adapt to the instance-dependent complexity measure of the smallest hypothesis class containing the true model. We design algorithms in…

Machine Learning · Statistics 2022-03-18 Yinglun Zhu , Julian Katz-Samuels , Robert Nowak

In this work, we reveal a rich combinatorial structure underlying exact minimax optimal algorithms for classical nonexpansive fixed-point problems. This viewpoint unifies all extremal optimal methods and provides a systematic and practical…

Optimization and Control · Mathematics 2026-05-05 TaeHo Yoon , Benjamin Grimmer

In the field of Artificial Intelligence, traditional approaches to choosing moves in games involve the we of the minimax algorithm. However, recent research results indicate that minimizing may not always be the best approach. In this paper…

Artificial Intelligence · Computer Science 2013-04-15 Dana Nau , Paul Purdom , Chun-Hung Tzeng

Iterative Hard Thresholding (IHT) is a class of projected gradient descent methods for optimizing sparsity-constrained minimization models, with the best known efficiency and scalability in practice. As far as we know, the existing…

Machine Learning · Computer Science 2017-06-22 Bo Liu , Xiao-Tong Yuan , Lezi Wang , Qingshan Liu , Dimitris N. Metaxas

We consider the problem of \textit{best arm identification} with a \textit{fixed budget $T$}, in the $K$-armed stochastic bandit setting, with arms distribution defined on $[0,1]$. We prove that any bandit strategy, for at least one bandit…

Machine Learning · Statistics 2016-05-31 Alexandra Carpentier , Andrea Locatelli

Active Sequential Hypothesis Testing (ASHT) is an extension of the classical sequential hypothesis testing problem with controls. Chernoff (Ann. Math. Statist., 1959) proposed a policy called Procedure A and showed its asymptotic optimality…

Information Theory · Computer Science 2015-05-12 Nidhin Koshy Vaidhiyan , Rajesh Sundaresan

This paper addresses the exploration-exploitation dilemma inherent in decision-making, focusing on multi-armed bandit problems. The problems involve an agent deciding whether to exploit current knowledge for immediate gains or explore new…

Machine Learning · Statistics 2023-07-06 Alex Barbier-Chebbah , Christian L. Vestergaard , Jean-Baptiste Masson

We propose an efficient ADMM method with guarantees for high-dimensional problems. We provide explicit bounds for the sparse optimization problem and the noisy matrix decomposition problem. For sparse optimization, we establish that the…

Machine Learning · Computer Science 2015-07-08 Hanie Sedghi , Anima Anandkumar , Edmond Jonckheere

We study the Maximum Budgeted Allocation problem, which is the problem of assigning indivisible items to players with budget constraints. In its most general form, an instance of the MBA problem might include many different prices for the…

Data Structures and Algorithms · Computer Science 2015-12-01 Christos Kalaitzis

We consider the question introduced by \cite{Mason2020} of identifying all the $\varepsilon$-optimal arms in a finite stochastic multi-armed bandit with Gaussian rewards. We give two lower bounds on the sample complexity of any algorithm…

Machine Learning · Statistics 2022-04-07 Aymen Al Marjani , Tomáš Kocák , Aurélien Garivier

We study a novel pure exploration problem: the $\epsilon$-Thresholding Bandit Problem (TBP) with fixed confidence in stochastic linear bandits. We prove a lower bound for the sample complexity and extend an algorithm designed for Best Arm…

Machine Learning · Statistics 2024-02-16 Eduardo Ochoa Rivera , Ambuj Tewari

The vulnerability of deep neural network models to adversarial example attacks is a practical challenge in many artificial intelligence applications. A recent line of work shows that the use of randomization in adversarial training is the…

Machine Learning · Computer Science 2023-06-30 Jiahao Xie , Chao Zhang , Weijie Liu , Wensong Bai , Hui Qian

We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits. While asymptotically optimal algorithms exist for standard multi-arm bandits, the existence of such…

Machine Learning · Statistics 2020-07-03 Rémy Degenne , Pierre Ménard , Xuedong Shang , Michal Valko

We derive asymptotically optimal statistical decision rules for discrete choice problems when payoffs depend on a partially-identified parameter $\theta$ and the decision maker can use a point-identified parameter $\mu$ to deduce…

Econometrics · Economics 2025-12-19 Timothy Christensen , Hyungsik Roger Moon , Frank Schorfheide

Equipping approximate dynamic programming (ADP) with inputconstraints has a tremendous significance. This enables ADP to be applied tothe systems with actuator limitations, which is quite common for dynamicalsystems. In a conventional…

Optimization and Control · Mathematics 2018-05-24 Xuefeng Bao , Zhi-Hong Mao , Nitin Sharma

We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an…

Machine Learning · Statistics 2019-09-13 Alexander Luedtke , Emilie Kaufmann , Antoine Chambaz

We focus on the problem of \emph{Answer-Level Fine-Tuning} (ALFT), where the goal is to optimize a language model based on the correctness or properties of its final answers, rather than the specific reasoning traces used to produce them.…

Machine Learning · Computer Science 2026-05-01 Mehryar Mohri , Jon Schneider , Yifan Wu

We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely…

Machine Learning · Statistics 2017-10-17 Liyuan Xu , Junya Honda , Masashi Sugiyama

Computerized Adaptive Testing (CAT) measures an examinee's ability while adapting to their level. Both too many questions and too many hard questions can make a test frustrating. Are there some CAT algorithms which can be proven to be…

Data Structures and Algorithms · Computer Science 2024-03-12 Jérémy Barbay