arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.07087cs.LGstat.ML
收藏

有偏噪声梯度预言机的(Bandit)凸优化

(Bandit) Convex Optimization with Biased Noisy Gradient Oracles

University of Alberta(阿尔伯塔大学);Indian Institute of Technology Madras(马德拉斯印度理工学院);Imperial College London(伦敦帝国理工学院)

Xiaowei Hu, Prashanth L. A., András György, Csaba Szepesvári

摘要:

用于凸优化和在线学习的算法通常依赖于构造噪声梯度估计,然后在适当调整的一阶算法中使用该噪声梯度估计,以代替实际梯度。依赖于要优化的函数的性质和在强盗反馈中的“噪声”的性质,梯度估计的偏差和方差表现出各种折衷。在本文中,我们提出了一个新的框架,取代了具体的梯度估计方法与抽象的预言。在新框架的帮助下,我们统一了以前的作品,再现他们的结果在一个干净和简洁的方式,同时,也许更重要的是,该框架还允许我们正式表明,要实现最佳的根$n$率的算法,使用现有的梯度估计,或证明技术来分析他们必须超越今天存在的。

英文摘要:

Algorithms for bandit convex optimization and online learning often rely on constructing noisy gradient estimates, which are then used in appropriately adjusted first-order algorithms, replacing actual gradients. Depending on the properties of the function to be optimized and the nature of ``noise'' in the bandit feedback, the bias and variance of gradient estimates exhibit various tradeoffs. In this paper we propose a novel framework that replaces the specific gradient estimation methods with an abstract oracle. With the help of the new framework we unify previous works, reproducing their results in a clean and concise fashion, while, perhaps more importantly, the framework also allows us to formally show that to achieve the optimal root-$n$ rate either the algorithms that use existing gradient estimators, or the proof techniques used to analyze them have to go beyond what exists today.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑