中文
相关论文

相关论文: Learning to Identify Top Elo Ratings: A Dueling Ba…

200 篇论文

We study the Logistic Contextual Slate Bandit problem, where, at each round, an agent selects a slate of $N$ items from an exponentially large set (of size $2^{\Omega(N)}$) of candidate slates provided by the environment. A single binary…

机器学习 · 计算机科学 2026-05-13 Tanmay Goyal , Gaurav Sinha

Many high-stakes decision-making problems, such as those found within cybersecurity and economics, can be modeled as competitive resource allocation games. In these games, multiple players must allocate limited resources to overcome their…

计算机科学与博弈论 · 计算机科学 2024-01-10 N'yoma Diamond , Fabricio Murai

Exposure bias is a well-known issue in recommender systems where items and suppliers are not equally represented in the recommendation results. This bias becomes particularly problematic over time as a few items are repeatedly…

信息检索 · 计算机科学 2024-08-09 Masoud Mansoury , Bamshad Mobasher , Herke van Hoof

We consider the problem of learning to choose actions using contextual information when provided with limited feedback in the form of relative pairwise comparisons. We study this problem in the dueling-bandits framework of Yue et al.…

机器学习 · 计算机科学 2015-06-16 Miroslav Dudík , Katja Hofmann , Robert E. Schapire , Aleksandrs Slivkins , Masrour Zoghi

Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to…

机器学习 · 计算机科学 2024-03-13 Yu Xia , Fang Kong , Tong Yu , Liya Guo , Ryan A. Rossi , Sungchul Kim , Shuai Li

League of Legends (LoL) has been a dominant esport for a decade, yet the inherent complexity of the game has stymied the creation of analytical measures of player skill and performance. Current industry standards are limited to…

应用统计 · 统计学 2024-05-07 Amy X. Zhang , Parth Naidu

We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm…

机器学习 · 计算机科学 2011-10-28 Alina Beygelzimer , John Langford , Lihong Li , Lev Reyzin , Robert E. Schapire

We consider the well-studied dueling bandit problem, where a learner aims to identify near-optimal actions using pairwise comparisons, under the constraint of differential privacy. We consider a general class of utility-based preference…

机器学习 · 计算机科学 2024-03-25 Aadirupa Saha , Hilal Asi

Bandit algorithms solve diverse sequential decision-making problems, but are often too sample-inefficient for from-scratch personalization. To substantially reduce exploration times, latent bandit algorithms exploit cross-instance structure…

机器学习 · 计算机科学 2026-05-11 Emil Carlsson , Newton Mwai , Fredrik D. Johansson

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

机器学习 · 统计学 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

This paper considers an online multi-player resource-sharing game with bandit feedback. Multiple players choose from a finite collection of resources in a time slotted system. In each time slot, each resource brings a random reward that is…

计算机科学与博弈论 · 计算机科学 2025-02-18 Mevan Wijewardena , Michael. J Neely

Modern chess engines achieve superhuman performance through deep tree search and regressive evaluation, while human players rely on intuition to select candidate moves followed by a shallow search to validate them. To model this…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Andrew Hamara , Greg Hamerly , Pablo Rivas , Andrew C. Freeman

We propose a model for learning with bandit feedback while accounting for deterministically evolving and unobservable states that we call Bandits with Deterministically Evolving States ($B$-$DES$). The workhorse applications of our model…

机器学习 · 计算机科学 2025-01-29 Khashayar Khosravi , Renato Paes Leme , Chara Podimata , Apostolis Tsorvantzis

We consider an online allocation problem that involves a set $P$ of $n$ players and a set $E$ of $m$ indivisible entities over discrete time steps $1,2,\ldots,\tau$. At each time step $t \in [1,\tau]$, for every entity $e \in E$, there is a…

数据结构与算法 · 计算机科学 2021-12-02 Siu-Wing Cheng

We study how representation learning can improve the efficiency of bandit problems. We study the setting where we play $T$ linear bandits with dimension $d$ concurrently, and these $T$ bandit tasks share a common $k (\ll d)$ dimensional…

机器学习 · 计算机科学 2021-05-06 Jiaqi Yang , Wei Hu , Jason D. Lee , Simon S. Du

We tackle a new emerging problem, which is finding an optimal monopartite matching in a weighted graph. The semi-bandit version, where a full matching is sampled at each iteration, has been addressed by \cite{ADMA}, creating an algorithm…

机器学习 · 计算机科学 2022-08-03 Camille-Sovanneary Gauthier , Romaric Gaudel , Elisa Fromont

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…

机器学习 · 计算机科学 2025-08-27 Suryanarayana Sankagiri , Jalal Etesami , Pouria Fatemi , Matthias Grossglauser

Partial monitoring is a generic framework for sequential decision-making with incomplete feedback. It encompasses a wide class of problems such as dueling bandits, learning with expect advice, dynamic pricing, dark pools, and label…

机器学习 · 计算机科学 2024-06-27 Pratik Gajane , Tanguy Urvoy

Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth references (e.g., labeled validation data) that are costly to obtain. We propose the Prompt…

计算与语言 · 计算机科学 2026-04-10 Yuanchen Wu , Saurabh Verma , Justin Lee , Fangzhou Xiong , Poppy Zhang , Amel Awadelkarim , Xu Chen , Yubai Yuan , Shawndra Hill

Adversarial board games, as a paradigmatic domain of strategic reasoning and intelligence, have long served as both a popular competitive activity and a benchmark for evaluating artificial intelligence (AI) systems. Building on this…