Information Directed Sampling for Sparse Linear Bandits

Information Directed Sampling for Sparse Linear Bandits
复制标题

稀疏线性老虎机的信息定向采样

DOI:
--
复制
发表时间:
2021
期刊:
Neural Information Processing Systems
影响因子:
--
通讯作者:
Wei Deng
Wei Deng
中科院分区:
--
文献类型:
--
作者:
Botao Hao;Tor Lattimore;Wei Deng

文献摘要

参考文献

被引文献

相似文献

随机稀疏线性强盗为高维在线决策问题提供了一种实用的模型,具有丰富的信息后悔结构。在这项工作中,我们探索了信息导向抽样(IDS)的使用,它自然地平衡了信息和后悔之间的权衡。我们开发了一类信息理论的贝叶斯遗憾界,它几乎与现有的各种问题实例的下界相匹配,从而证明了入侵检测系统的自适应性。为了有效地实现稀疏入侵检测,我们提出了一种基于尖峰-板条高斯-拉普拉斯先验的稀疏后验采样的经验贝叶斯方法。数值结果表明,相对于几个基线,稀疏入侵检测显著减少了遗憾。
Stochastic sparse linear bandits offer a practical model for high-dimensional online decision-making problems and have a rich information-regret structure. In this work we explore the use of information-directed sampling (IDS), which naturally balances the information-regret trade-off. We develop a class of information-theoretic Bayesian regret bounds that nearly match existing lower bounds on a variety of problem instances, demonstrating the adaptivity of IDS. To efficiently implement sparse IDS, we propose an empirical Bayesian approach for sparse posterior sampling using a spike-and-slab Gaussian-Laplace prior. Numerical results demonstrate significant regret reductions by sparse IDS relative to several baselines.
招募的 T 细胞通过上调雌激素受体 beta/1L-1/c-MET 信号促进膀胱癌转移
DOI: 10.1016/j.canlet.2018.03.045
发表时间: 2018-01-01
期刊: CANCER LETTERS
影响因子: 9.7
作者:
Tao, Le;Qiu, Jianxin;Yeh, Shuyuan
通讯作者: Yeh, Shuyuan