English
Related papers

Related papers: Adaptive Experimentation When You Can't Experiment

200 papers

In many fields such as digital marketing, healthcare, finance, and robotics, it is common to have a well-tested and reliable baseline policy running in production (e.g., a recommender system). Nonetheless, the baseline policy is often…

Machine Learning · Computer Science 2020-02-11 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Machine Learning · Computer Science 2023-07-25 Ayush Sekhari , Karthik Sridharan , Wen Sun , Runzhe Wu

Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently identifying top-performing candidates without exhaustive…

Machine Learning · Computer Science 2026-02-03 Seyed Mohammad Hadi Hosseini , Amir Najafi , Mahdieh Soleymani Baghshah

Transfer learning seeks to accelerate sequential decision-making by leveraging offline data from related agents. However, data from heterogeneous sources that differ in observed features, distributions, or unobserved confounders often…

Machine Learning · Computer Science 2025-07-10 Xueping Gong , Wei You , Jiheng Zhang

Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-commerce, healthcare, and policymaking because they can both improve outcomes for study participants and increase the chance of identifying good or even…

Machine Learning · Statistics 2021-06-02 Aurélien Bibaut , Antoine Chambaz , Maria Dimakopoulou , Nathan Kallus , Mark van der Laan

Selecting the optimal recommender via online exploration-exploitation is catching increasing attention where the traditional A/B testing can be slow and costly, and offline evaluations are prone to the bias of history data. Finding the…

Information Retrieval · Computer Science 2022-03-29 Da Xu , Chuanwei Ruan , Evren Korpeoglu , Sushant Kumar , Kannan Achan

Causal discovery aims to uncover cause-and-effect relationships encoded in causal graphs by leveraging observational, interventional data, or their combination. The majority of existing causal discovery methods are developed assuming…

Machine Learning · Computer Science 2024-06-25 Muhammad Qasim Elahi , Lai Wei , Murat Kocaoglu , Mahsa Ghasemi

We consider the problem of online convex optimization against an arbitrary adversary with bandit feedback, known as bandit convex optimization. We give the first $\tilde{O}(\sqrt{T})$-regret algorithm for this setting based on a novel…

Machine Learning · Computer Science 2016-03-16 Elad Hazan , Yuanzhi Li

We study pure exploration in structured stochastic multi-armed bandits, aiming to efficiently identify the correct hypothesis from a finite set of alternatives. For a broad class of tasks, asymptotic analyses reduce to a maximin…

Machine Learning · Computer Science 2025-09-25 Xinyu Liu , Chao Qin , Wei You

We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback. In this sequential decision making problem, the learner cannot directly observe its rewards, but instead…

Machine Learning · Computer Science 2022-07-20 Germano Gabbianelli , Matteo Papini , Gergely Neu

We formulate a new problem at the intersectionof semi-supervised learning and contextual bandits,motivated by several applications including clini-cal trials and ad recommendations. We demonstratehow Graph Convolutional Network (GCN), a…

Machine Learning · Computer Science 2020-10-26 Sohini Upadhyay , Mikhail Yurochkin , Mayank Agarwal , Yasaman Khazaeni , DjallelBouneffouf

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…

Machine Learning · Computer Science 2011-10-28 Alina Beygelzimer , John Langford , Lihong Li , Lev Reyzin , Robert E. Schapire

Motivated by the importance of explainability in modern machine learning, we design bandit algorithms that are efficient and interpretable. A bandit algorithm is interpretable if it explores with the objective of reducing uncertainty in the…

Machine Learning · Computer Science 2024-02-12 Subhojyoti Mukherjee , Ruihao Zhu , Branislav Kveton

Traditional curriculum learning proceeds from easy to hard samples, yet defining a reliable notion of difficulty remains elusive. Prior work has used submodular functions to induce difficulty scores in curriculum learning. We reinterpret…

Machine Learning · Computer Science 2025-12-01 Prateek Chanda , Prayas Agrawal , Saral Sureka , Lokesh Reddy Polu , Atharv Kshirsagar , Ganesh Ramakrishnan

When data are collected adaptively, such as in bandit algorithms, classical statistical approaches such as ordinary least squares and $M$-estimation will often fail to achieve asymptotic normality. Although recent lines of work have…

Methodology · Statistics 2026-02-10 James Leiner , Robin Dunn , Aaditya Ramdas

We study the sample complexity of pure exploration in an online learning problem with a feedback graph. This graph dictates the feedback available to the learner, covering scenarios between full-information, pure bandit feedback, and…

Machine Learning · Statistics 2025-03-12 Alessio Russo , Yichen Song , Aldo Pacchiano

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However,…

Machine Learning · Computer Science 2025-04-17 Arun Verma , Zhongxiang Dai , Xiaoqiang Lin , Patrick Jaillet , Bryan Kian Hsiang Low

Combinatorial bandits with semi-bandit feedback generalize multi-armed bandits, where the agent chooses sets of arms and observes a noisy reward for each arm contained in the chosen set. The action set satisfies a given structure such as…

Machine Learning · Statistics 2021-01-22 Marc Jourdan , Mojmír Mutný , Johannes Kirschner , Andreas Krause

Understanding treatment effect heterogeneity has become an increasingly popular task in various fields, as it helps design personalized advertisements in e-commerce or targeted treatment in biomedical studies. However, most of the existing…

Methodology · Statistics 2024-07-12 Waverly Wei , Xinwei Ma , Jingshen Wang

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise…

Machine Learning · Computer Science 2025-08-22 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett