English
Related papers

Related papers: Optimistic Information Directed Sampling

200 papers

This paper studies bandit problems where an agent has access to offline data that might be utilized to potentially improve the estimation of each arm's reward distribution. A major obstacle in this setting is the existence of compound…

Machine Learning · Computer Science 2023-12-21 Wen Huang , Xintao Wu

We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logistic function, $\exp(\beta \langle a, \theta…

Machine Learning · Statistics 2025-02-21 Amaury Gouverneur , Borja Rodríguez-Gálvez , Tobias J. Oechtering , Mikael Skoglund

We consider the contextual bandit problem where at each time, the agent only has access to a noisy version of the context and the error variance (or an estimator of this variance). This setting is motivated by a wide range of applications…

Machine Learning · Statistics 2024-03-19 Yongyi Guo , Ziping Xu , Susan Murphy

This paper investigates regret minimization, statistical inference, and their interplay in high-dimensional online decision-making based on the sparse linear context bandit model. We integrate the $\varepsilon$-greedy bandit algorithm for…

Machine Learning · Computer Science 2025-05-20 Congyuan Duan , Wanteng Ma , Jiashuo Jiang , Dong Xia

Decision-making from offline datasets typically warm-starts a policy or score model from fixed offline data and then refines it with limited online interaction. Offline data reduces uncertainty, but it does not remove the need for…

Machine Learning · Computer Science 2026-05-29 Keru Chen

This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems. It builds upon the information-theoretic framework of [Russo and Van Roy, 2015] and, more specifically, on the rate-distortion…

Machine Learning · Statistics 2024-03-07 Amaury Gouverneur , Borja Rodríguez-Gálvez , Tobias J. Oechtering , Mikael Skoglund

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

We establish a connection between the stability of mirror descent and the information ratio by Russo and Van Roy [2014]. Our analysis shows that mirror descent with suitable loss estimators and exploratory distributions enjoys the same…

Optimization and Control · Mathematics 2020-09-28 Tor Lattimore , András György

Partial monitoring is a rich framework for sequential decision making under uncertainty that generalizes many well known bandit models, including linear, combinatorial and dueling bandits. We introduce information directed sampling (IDS)…

Machine Learning · Statistics 2020-02-27 Johannes Kirschner , Tor Lattimore , Andreas Krause

Contextual bandits serve as a fundamental model for many sequential decision making tasks. The most popular theoretically justified approaches are based on the optimism principle. While these algorithms can be practical, they are known to…

Machine Learning · Computer Science 2020-03-17 Botao Hao , Tor Lattimore , Csaba Szepesvari

We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action. We allow the graph structure to vary with time and consider both…

Machine Learning · Computer Science 2017-11-10 Fang Liu , Swapna Buccapatnam , Ness Shroff

The information-theoretic analysis by Russo and Van Roy (2014) in combination with minimax duality has proved a powerful tool for the analysis of online learning algorithms in full and partial information settings. In most applications…

Machine Learning · Computer Science 2019-05-29 Julian Zimmert , Tor Lattimore

We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or imposing model restrictions on losses or rewards. In this…

Machine Learning · Statistics 2026-04-06 Samuel Girard , Aurelien Bibaut , Arthur Gretton , Nathan Kallus , Houssam Zenati

Autoregressive processes naturally arise in a large variety of real-world scenarios, including stock markets, sales forecasting, weather prediction, advertising, and pricing. When facing a sequential decision-making problem in such a…

We consider the problem of interactive decision making, encompassing structured bandits and reinforcement learning with general function approximation. Recently, Foster et al. (2021) introduced the Decision-Estimation Coefficient, a measure…

Machine Learning · Computer Science 2023-08-15 Dylan J. Foster , Noah Golowich , Jian Qian , Alexander Rakhlin , Ayush Sekhari

We study the problem of incentive-compatible online learning with bandit feedback. In this class of problems, the experts are self-interested agents who might misrepresent their preferences with the goal of being selected most often. The…

Machine Learning · Computer Science 2024-05-13 Julian Zimmert , Teodor V. Marinov

The predict-then-optimize paradigm bridges online learning and contextual optimization in dynamic environments. Previous works have investigated the sequential updating of predictors using feedback from downstream decisions to minimize…

Optimization and Control · Mathematics 2025-11-26 Zhuojun Xie , Adam Abdin , Yiping Fang

Model selection in supervised learning provides costless guarantees as if the model that best balances bias and variance was known a priori. We study the feasibility of similar guarantees for cumulative regret minimization in the stochastic…

Machine Learning · Computer Science 2023-10-25 Sanath Kumar Krishnamurthy , Adrienne Margaret Propp , Susan Athey

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu

In this paper we propose a novel experimental design-based algorithm to minimize regret in online stochastic linear and combinatorial bandits. While existing literature tends to focus on optimism-based algorithms--which have been shown to…

Machine Learning · Computer Science 2021-03-02 Andrew Wagenmaker , Julian Katz-Samuels , Kevin Jamieson