English
Related papers

Related papers: An Optimization-based Algorithm for Non-stationary…

200 papers

Traditional multi-armed bandit (MAB) frameworks, predominantly examined under stochastic or adversarial settings, often overlook the temporal dynamics inherent in many real-world applications such as recommendation systems and online…

Machine Learning · Computer Science 2023-12-13 Qinyi Chen , Negin Golrezaei , Djallel Bouneffouf

We study a nonparametric contextual bandit problem where the expected reward functions belong to a H\"older class with smoothness parameter $\beta$. We show how this interpolates between two extremes that were previously studied in…

Machine Learning · Statistics 2020-09-14 Yichun Hu , Nathan Kallus , Xiaojie Mao

Designing efficient general-purpose contextual bandit algorithms that work with large -- or even continuous -- action spaces would facilitate application to important scenarios such as information retrieval, recommendation systems, and…

Machine Learning · Computer Science 2022-07-14 Yinglun Zhu , Paul Mineiro

We study the causal bandit problem when the causal graph is unknown and develop an efficient algorithm for finding the parent node of the reward node using atomic interventions. We derive the exact equation for the expected number of…

Machine Learning · Statistics 2023-06-09 Mikhail Konobeev , Jalal Etesami , Negar Kiyavash

We study a $K$-armed non-stationary bandit model where rewards change smoothly, as captured by H\"{o}lder class assumptions on rewards as functions of time. Such smooth changes are parametrized by a H\"{o}lder exponent $\beta$ and…

Machine Learning · Statistics 2025-02-27 Joe Suk

We study dynamic regret minimization in unconstrained adversarial linear bandit problems. In this setting, a learner must minimize the cumulative loss relative to an arbitrary sequence of comparators…

Machine Learning · Computer Science 2026-03-30 Alberto Rumi , Andrew Jacobsen , Nicolò Cesa-Bianchi , Fabio Vitale

Causal knowledge about the relationships among decision variables and a reward variable in a bandit setting can accelerate the learning of an optimal decision. Current works often assume the causal graph is known, which may not always be…

Machine Learning · Statistics 2024-11-07 Muhammad Qasim Elahi , Mahsa Ghasemi , Murat Kocaoglu

Contextual bandit algorithms are extremely popular and widely used in recommendation systems to provide online personalised recommendations. A recurrent assumption is the stationarity of the reward function, which is rather unrealistic in…

Machine Learning · Statistics 2020-04-29 Giuseppe Di Benedetto , Vito Bellini , Giovanni Zappella

We study the non-stationary dueling bandits problem with $K$ arms, where the time horizon $T$ consists of $M$ stationary segments, each of which is associated with its own preference matrix. The learner repeatedly selects a pair of arms and…

Machine Learning · Computer Science 2022-02-03 Patrick Kolpaczki , Viktor Bengs , Eyke Hüllermeier

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

In this work, we develop linear bandit algorithms that automatically adapt to different environments. By plugging a novel loss estimator into the optimization problem that characterizes the instance-optimal strategy, our first algorithm not…

Machine Learning · Computer Science 2021-06-15 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang , Xiaojin Zhang

Fast changing states or volatile environments pose a significant challenge to online optimization, which needs to perform rapid adaptation under limited observation. In this paper, we give query and regret optimal bandit algorithms under…

Machine Learning · Computer Science 2024-01-18 Zhou Lu , Qiuyi Zhang , Xinyi Chen , Fred Zhang , David Woodruff , Elad Hazan

The piecewise-stationary bandit problem is an important variant of the multi-armed bandit problem that further considers abrupt changes in the reward distributions. The main theme of the problem is the trade-off between exploration for…

Machine Learning · Computer Science 2024-10-10 Kuan-Ta Li , Ping-Chun Hsieh , Yu-Chih Huang

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific…

Machine Learning · Statistics 2016-04-12 Robert Nishihara , David Lopez-Paz , Léon Bottou

In this paper, we address the contextual dueling bandit problem by proposing variance-aware algorithms that leverage neural networks to approximate nonlinear utility functions. Our approach employs a \textit{variance-aware exploration…

Machine Learning · Computer Science 2026-05-12 Youngmin Oh , Jinje Park , Taejin Paik , Jaemin Park

Bandit algorithms have been predominantly analyzed in the convex setting with function-value based stationary regret as the performance measure. In this paper, motivated by online reinforcement learning problems, we propose and analyze…

Machine Learning · Statistics 2019-09-12 Abhishek Roy , Krishnakumar Balasubramanian , Saeed Ghadimi , Prasant Mohapatra

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 study the multi-armed bandit problem where the rewards are realizations of general non-stationary stochastic processes, a setting that generalizes many existing lines of work and analyses. In particular, we present a theoretical analysis…

Machine Learning · Computer Science 2020-09-04 Corinna Cortes , Giulia DeSalvo , Vitaly Kuznetsov , Mehryar Mohri , Scott Yang

We study linear bandits when the underlying reward function is not linear. Existing work relies on a uniform misspecification parameter $\epsilon$ that measures the sup-norm error of the best linear approximation. This results in an…

Machine Learning · Computer Science 2023-07-21 Chong Liu , Ming Yin , Yu-Xiang Wang

Thanks to the power of representation learning, neural contextual bandit algorithms demonstrate remarkable performance improvement against their classical counterparts. But because their exploration has to be performed in the entire neural…

Machine Learning · Computer Science 2022-03-22 Yiling Jia , Weitong Zhang , Dongruo Zhou , Quanquan Gu , Hongning Wang