Dynamic Structure Estimation from Bandit Feedback

arxiv(2022)

引用 0|浏览1
暂无评分
摘要
This work present novel method for structure estimation of an underlying dynamical system. We tackle problems of estimating dynamic structure from bandit feedback contaminated by sub-Gaussian noise. In particular, we focus on periodically behaved discrete dynamical system in the Euclidean space, and carefully identify certain obtainable subset of full information of the periodic structure. We then derive a sample complexity bound for periodic structure estimation. Technically, asymptotic results for exponential sums are adopted to effectively average out the noise effects while preventing the information to be estimated from vanishing. For linear systems, the use of the Weyl sum further allows us to extract eigenstructures. Our theoretical claims are experimentally validated on simulations of toy examples, including Cellular Automata.
更多
查看译文
关键词
dynamic structure estimation,feedback
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要