English
Related papers

Related papers: An Information-Theoretic Analysis for Thompson Sam…

200 papers

We study the effect of impairment on stochastic multi-armed bandits and develop new ways to mitigate it. Impairment effect is the phenomena where an agent only accrues reward for an action if they have played it at least a few times in the…

Machine Learning · Computer Science 2020-06-23 Priyank Agrawal , Theja Tulabandhula

We study the sequential general online regression, known also as the sequential probability assignments, under logarithmic loss when compared against a broad class of experts. We focus on obtaining tight, often matching, lower and upper…

Machine Learning · Computer Science 2023-02-02 Changlong Wu , Mohsen Heidari , Ananth Grama , Wojciech Szpankowski

We address the problem of the achievable regret rates with online logistic regression. We derive lower bounds with logarithmic regret under $L_1$, $L_2$, and $L_\infty$ constraints on the parameter values. The bounds are dominated by $d/2…

Machine Learning · Computer Science 2020-02-20 Gil I. Shamir

We study the benefits of sparsity in nonparametric contextual bandit problems, in which the set of candidate features is countably or uncountably infinite. Our contribution is two-fold. First, using a novel reduction to sequences of…

Machine Learning · Statistics 2026-01-16 Hamish Flynn , Julia Olkhovskaya , Paul Rognon-Vael

We introduce a simple and efficient algorithm for stochastic linear bandits with finitely many actions that is asymptotically optimal and (nearly) worst-case optimal in finite time. The approach is based on the frequentist…

Machine Learning · Statistics 2021-07-05 Johannes Kirschner , Tor Lattimore , Claire Vernade , Csaba Szepesvári

This work studies the problem of sequential control in an unknown, nonlinear dynamical system, where we model the underlying system dynamics as an unknown function in a known Reproducing Kernel Hilbert Space. This framework yields a general…

Machine Learning · Computer Science 2020-06-23 Sham Kakade , Akshay Krishnamurthy , Kendall Lowrey , Motoya Ohnishi , Wen Sun

We study the challenging exploration incentive problem in both bandit and reinforcement learning, where the rewards are scale-free and potentially unbounded, driven by real-world scenarios and differing from existing work. Past works in…

Machine Learning · Computer Science 2024-05-07 Mengfan Xu , Diego Klabjan

We study online learning with bandit feedback across multiple tasks, with the goal of improving average performance across tasks if they are similar according to some natural task-similarity measure. As the first to target the adversarial…

Machine Learning · Computer Science 2022-05-30 Maria-Florina Balcan , Keegan Harris , Mikhail Khodak , Zhiwei Steven Wu

We consider a linear stochastic bandit problem where the dimension $K$ of the unknown parameter $\theta$ is larger than the sampling budget $n$. In such cases, it is in general impossible to derive sub-linear regret bounds since usual…

Statistics Theory · Mathematics 2012-05-23 Alexandra Carpentier , Rémi Munos

One way to make decisions under uncertainty is to select an optimal option from a possible range of options, by maximizing the expected utilities derived from a probability model. However, under severe uncertainty, identifying precise…

Statistics Theory · Mathematics 2024-03-06 Nawapon Nakharutai , Sébastien Destercke , Matthias C. M. Troffaes

We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling…

Machine Learning · Statistics 2021-11-01 Brendan O'Donoghue , Tor Lattimore

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 consider sequential decision making in a setting where regret is measured with respect to a set of stateful reference policies, and feedback is limited to observing the rewards of the actions performed (the so called "bandit" setting).…

Machine Learning · Computer Science 2014-07-30 Uriel Feige , Tomer Koren , Moshe Tennenholtz

In the latent bandit problem, the learner has access to reward distributions and -- for the non-stationary variant -- transition models of the environment. The reward distributions are conditioned on the arm and unknown latent states. The…

Machine Learning · Computer Science 2022-07-11 Alexander Galozy , Slawomir Nowaczyk

Thompson Sampling is one of the most widely used and studied bandit algorithms, known for its simple structure, low regret performance, and solid theoretical guarantees. Yet, in stark contrast to most other families of bandit algorithms,…

Machine Learning · Computer Science 2026-05-28 Yanlin Qu , Hongseok Namkoong , Assaf Zeevi

Online model selection in Bayesian bandits raises a fundamental exploration challenge: When an environment instance is sampled from a prior distribution, how can we design an adaptive strategy that explores multiple bandit learners and…

Machine Learning · Computer Science 2026-02-23 Aida Afshar , Yuke Zhang , Aldo Pacchiano

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

The multi-armed bandit problem is a popular model for studying exploration/exploitation trade-off in sequential decision problems. Many algorithms are now available for this well-studied problem. One of the earliest algorithms, given by W.…

Machine Learning · Computer Science 2012-04-10 Shipra Agrawal , Navin Goyal

A common challenge for decision makers is selecting actions whose rewards are unknown and evolve over time based on prior policies. For instance, repeated use may reduce an action's effectiveness (habituation), while inactivity may restore…

Machine Learning · Computer Science 2025-11-06 Fengxu Li , Stephanie M. Carpenter , Matthew P. Buman , Yonatan Mintz

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions,…

Machine Learning · Statistics 2020-06-23 Akshay Krishnamurthy , John Langford , Aleksandrs Slivkins , Chicheng Zhang