paper-with-me

Papers

BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits

2016-02-06 · Alexander Rakhlin, Karthik Sridharan

We present efficient algorithms for the problem of contextual bandits with i.i.d. covariates, an arbitrary sequence of rewards, and an arbitrary class of policies. Our algorithm BISTRO requires d calls to the empirical risk minimization (ERM) oracle per round, where d is the number of actions. The method uses unlabeled data to make the problem computationally simple. When the ERM problem itself is computationally hard, we extend the approach by employing multiplicative approximation algorithms for the ERM. The integrality gap of the relaxation only enters in the regret bound rather than the benchmark. Finally, we show that the adversarial version of the contextual bandit problem is learnable (and efficient) whenever the full-information supervised online learning problem has a non-trivial regret guarantee (and efficient).

📄 PDF Abstract BibTeX arXiv:1602.02196

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits

2023-10-29 · NeurIPS 2023 11

We present an oracle-efficient relaxation for the adversarial contextual bandits problem, where the contexts are sequentially drawn i.i.d from a known distribution and the cost sequence is chosen by an online adversary. …

Multi-Armed Bandits

Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning

2024-06-24 · Xiao Han, Chen Zhu, Xiao Hu, Chuan Qin 외

Job recommender systems are crucial for aligning job opportunities with job-seekers in online job-seeking. However, users tend to adjust their job preferences to secure employment opportunities continually, which limits …

ClusteringRecommendation Systems

Contextual Bandits with Stage-wise Constraints

2024-01-15 · Aldo Pacchiano, Mohammad Ghavamzadeh, Peter Bartlett

We study contextual bandits in the presence of a stage-wise constraint (a constraint at each round), when the constraint must be satisfied both with high probability and in expectation. Obviously the setting where the co…

Multi-Armed Bandits

Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits

2016-06-01 · NeurIPS 2016 12 · Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire

We give an oracle-based algorithm for the adversarial contextual bandit problem, where either contexts are drawn i.i.d. or the sequence of contexts is known a priori, but where the losses are picked adversarially. Our al…

Multi-Armed Bandits

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits

2020-10-23 · NeurIPS 2020 12 · Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric

In the contextual linear bandit setting, algorithms built on the optimism principle fail to exploit the structure of the problem and have been shown to be asymptotically suboptimal. In this paper, we follow recent approa…