paper-with-me

홈 › Papers

Nested bandits

2022-06-19 · Matthieu Martin, Panayotis Mertikopoulos, Thibaud Rahier, Houssam Zenati

In many online decision processes, the optimizing agent is called to choose between large numbers of alternatives with many inherent similarities; in turn, these similarities imply closely correlated losses that may confound standard discrete choice models and bandit algorithms. We study this question in the context of nested bandits, a class of adversarial multi-armed bandit problems where the learner seeks to minimize their regret in the presence of a large number of distinct alternatives with a hierarchy of embedded (non-combinatorial) similarities. In this setting, optimal algorithms based on the exponential weights blueprint (like Hedge, EXP3, and their variants) may incur significant regret because they tend to spend excessive amounts of time exploring irrelevant alternatives with similar, suboptimal costs. To account for this, we propose a nested exponential weights (NEW) algorithm that performs a layered exploration of the learner's set of alternatives based on a nested, step-by-step selection method. In so doing, we obtain a series of tight bounds for the learner's regret showing that online learning problems with a high degree of similarity between alternatives can be resolved efficiently, without a red bus / blue bus paradox occurring.

📄 PDF Abstract BibTeX arXiv:2206.09348

Code (0)

등록된 구현이 없습니다.

Tasks

Discrete Choice Models

Similar Papers 제목 키워드 기반

The Pareto Frontier of model selection for general Contextual Bandits

2021-10-25 · NeurIPS 2021 12 · Teodor V. Marinov, Julian Zimmert

Recent progress in model selection raises the question of the fundamental limits of these techniques. Under specific scrutiny has been model selection for general contextual bandits with nested policy classes, resulting …

Model SelectionMulti-Armed Bandits

Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk

2026-05-28 · Tim Woydt, Paul-David Zuercher arxiv

Critical sequential decisions are rarely single-timescale: a strategic decision causally shapes the context in which every subsequent tactical choice is made; standard bandit and reinforcement-learning theory does not ca…

Regret Bound Balancing and Elimination for Model Selection in Bandits and RL

2020-12-24 · Aldo Pacchiano, Christoph Dann, Claudio Gentile, Peter Bartlett

We propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge of the optimal regret, we only require th…

Model Selectionvalid

Model selection for contextual bandits

2019-06-03 · NeurIPS 2019 12 · Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo

We introduce the problem of model selection for contextual bandits, where a learner must adapt to the complexity of the optimal policy while balancing exploration and exploitation. Our main result is a new model selectio…

modelModel SelectionMulti-Armed Bandits

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries

2024-06-03 · Tianyuan Jin, Kyoungseok Jang, Nicolò Cesa-Bianchi

We study stochastic linear bandits where, in each round, the learner receives a set of actions (i.e., feature vectors), from which it chooses an element and obtains a stochastic reward. The expected reward is a fixed but…

Model Selection