paper-with-me

Papers

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

2022-05-13 · Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu

We study the linear contextual bandit problem in the presence of adversarial corruption, where the reward at each round is corrupted by an adversary, and the corruption level (i.e., the sum of corruption magnitudes over the horizon) is $C\geq 0$. The best-known algorithms in this setting are limited in that they either are computationally inefficient or require a strong assumption on the corruption, or their regret is at least $C$ times worse than the regret without corruption. In this paper, to overcome these limitations, we propose a new algorithm based on the principle of optimism in the face of uncertainty. At the core of our algorithm is a weighted ridge regression where the weight of each chosen action depends on its confidence up to some threshold. We show that for both known $C$ and unknown $C$ cases, our algorithm with proper choice of hyperparameter achieves a regret that nearly matches the lower bounds. Thus, our algorithm is nearly optimal up to logarithmic factors for both cases. Notably, our algorithm achieves the near-optimal regret for both corrupted and uncorrupted cases ($C=0$) simultaneously.

📄 PDF Abstract BibTeX arXiv:2205.06811

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Feel-Good Thompson Sampling for Contextual Dueling Bandits

2024-04-09 · Xuheng Li, Heyang Zhao, Quanquan Gu

Contextual dueling bandits, where a learner compares two options based on context and receives feedback indicating which was preferred, extends classic dueling bandits by incorporating contextual information for decision…

Decision MakingMulti-Armed BanditsThompson Sampling

Federated Linear Contextual Bandits

2021-10-27 · NeurIPS 2021 12 · Ruiquan Huang, Weiqiang Wu, Jing Yang, Cong Shen

This paper presents a novel federated linear contextual bandits model, where individual clients face different $K$-armed stochastic bandits coupled through common global parameters. By leveraging the geometric structure …

Multi-Armed Bandits

Locally Differentially Private (Contextual) Bandits Learning

2020-06-01 · NeurIPS 2020 12 · Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li 외

We study locally differentially private (LDP) bandits learning in this paper. First, we propose simple black-box reduction frameworks that can solve a large family of context-free bandits learning problems with LDP guara…

Multi-Armed BanditsPrivacy Preserving Deep Learning

Linear Contextual Bandits with Knapsacks

2015-07-24 · NeurIPS 2016 12 · Shipra Agrawal, Nikhil R. Devanur

We consider the linear contextual bandit problem with resource consumption, in addition to reward generation. In each round, the outcome of pulling an arm is a reward as well as a vector of resource consumptions. The exp…

Multi-Armed Bandits

Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms

2022-11-08 · Osama A. Hanna, Lin F. Yang, Christina Fragouli

In this paper, we address the stochastic contextual linear bandit problem, where a decision maker is provided a context (a random set of actions drawn from a distribution). The expected reward of each action is specified…

Multi-Armed Bandits