English
Related papers

Related papers: Second Order Regret Bounds Against Generalized Exp…

200 papers

We study online reinforcement learning in linear Markov decision processes with adversarial losses and bandit feedback, without prior knowledge on transitions or access to simulators. We introduce two algorithms that achieve improved regret…

Machine Learning · Computer Science 2023-10-19 Haolin Liu , Chen-Yu Wei , Julian Zimmert

Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of…

Machine Learning · Computer Science 2022-06-09 Sarah Sachs , Hédi Hadiji , Tim van Erven , Cristóbal Guzmán

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

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…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

In this research note, we revisit the bandits with expert advice problem. Under a restricted feedback model, we prove a lower bound of order $\sqrt{K T \ln(N/K)}$ for the worst-case regret, where $K$ is the number of actions, $N>K$ the…

Machine Learning · Computer Science 2024-06-25 Nicolò Cesa-Bianchi , Khaled Eldowa , Emmanuel Esposito , Julia Olkhovskaya

We prove a new minimax theorem connecting the worst-case Bayesian regret and minimax regret under partial monitoring with no assumptions on the space of signals or decisions of the adversary. We then generalise the information-theoretic…

Machine Learning · Computer Science 2019-05-30 Tor Lattimore , Csaba Szepesvari

We develop the first general semi-bandit algorithm that simultaneously achieves $\mathcal{O}(\log T)$ regret for stochastic environments and $\mathcal{O}(\sqrt{T})$ regret for adversarial environments without knowledge of the regime or the…

Machine Learning · Computer Science 2019-09-27 Julian Zimmert , Haipeng Luo , Chen-Yu Wei

We study the problem of worst case regret in piecewise stationary multi armed bandits. While the minimax theory for stationary bandits is well established, understanding analogous limits in time-varying settings is challenging. Existing…

Machine Learning · Computer Science 2025-11-11 Gal Mendelson , Eyal Tadmor

We provide new lower bounds on the regret that must be suffered by adversarial bandit algorithms. The new results show that recent upper bounds that either (a) hold with high-probability or (b) depend on the total lossof the best arm or (c)…

Statistics Theory · Mathematics 2017-02-28 Sébastien Gerchinovitz , Tor Lattimore

We introduce a novel extension of the canonical multi-armed bandit problem that incorporates an additional strategic innovation: abstention. In this enhanced framework, the agent is not only tasked with selecting an arm at each time step,…

Machine Learning · Computer Science 2026-03-24 Junwen Yang , Tianyuan Jin , Vincent Y. F. Tan

We study how the regret guarantees of nonstochastic multi-armed bandits can be improved, if the effective range of the losses in each round is small (e.g. the maximal difference between two losses in a given round). Despite a recent…

Machine Learning · Computer Science 2020-01-03 Nicolò Cesa-Bianchi , Ohad Shamir

We address the online linear optimization problem when the actions of the forecaster are represented by binary vectors. Our goal is to understand the magnitude of the minimax regret for the worst possible set of actions. We study the…

Machine Learning · Statistics 2011-05-25 Jean-Yves Audibert , Sebastien Bubeck , Gabor Lugosi

We study the dynamic regret of multi-armed bandit and experts problem in non-stationary stochastic environments. We introduce a new parameter $\Lambda$, which measures the total statistical variance of the loss distributions over $T$ rounds…

Machine Learning · Computer Science 2019-06-24 Chen-Yu Wei , Yi-Te Hong , Chi-Jen Lu

We analyze and evaluate an online gradient descent algorithm with adaptive per-coordinate adjustment of learning rates. Our algorithm can be thought of as an online version of batch gradient descent with a diagonal preconditioner. This…

Machine Learning · Computer Science 2010-02-26 Matthew Streeter , H. Brendan McMahan

We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret $\mathcal{O}(\sqrt{T})$ for learning over $T$ rounds, when the total…

Machine Learning · Computer Science 2020-10-16 Chen-Yu Wei , Haipeng Luo , Alekh Agarwal

The problem of online prediction with sequential side information under logarithmic loss is studied, and general upper and lower bounds on the minimax regret incurred by the predictor is established. The upper bounds on the minimax regret…

Information Theory · Computer Science 2021-02-16 Alankrita Bhatt , Young-Han Kim

We study the attainable regret for online linear optimization problems with bandit feedback, where unlike the full-information setting, the player can only observe its own loss rather than the full loss vector. We show that the price of…

Machine Learning · Computer Science 2014-08-12 Ohad Shamir

Multi-armed Bandit motivates methods with provable upper bounds on regret and also the counterpart lower bounds have been extensively studied in this context. Recently, Multi-agent Multi-armed Bandit has gained significant traction in…

Machine Learning · Computer Science 2023-08-17 Mengfan Xu , Diego Klabjan

We consider the adversarial multi-armed bandit problem under delayed feedback. We analyze variants of the Exp3 algorithm that tune their step-size using only information (about the losses and delays) available at the time of the decisions,…

Machine Learning · Computer Science 2020-10-14 András György , Pooria Joulani

In many applications, e.g. in healthcare and e-commerce, the goal of a contextual bandit may be to learn an optimal treatment assignment policy at the end of the experiment. That is, to minimize simple regret. However, this objective…

Machine Learning · Computer Science 2023-11-06 Sanath Kumar Krishnamurthy , Ruohan Zhan , Susan Athey , Emma Brunskill