arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07862cs.LGmath.OCstat.ML
收藏

无导数优化和连续Bandits中高阶光滑性的利用

Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits

Istituto Italiano di Tecnologia(意大利技术研究院);CREST, ENSAE, IP Paris(巴黎政治经济统计高等学校经济与统计研究中心,巴黎综合理工学院联盟);University College London(伦敦大学学院)

Arya Akhavan, Massimiliano Pontil, Alexandre B. Tsybakov

摘要:

研究了强凸函数的零级优化问题。我们的目标是找到最小的功能,其值的顺序探索,测量噪声。我们研究了函数的高阶光滑性对优化误差和累积遗憾的影响。为了解决这个问题,我们考虑一个随机近似的投影梯度下降算法。梯度估计的随机过程涉及两个函数的评价和平滑内核。我们推导出该算法在约束和无约束的设置和证明极小极大下界的任何顺序搜索方法。我们的研究结果表明,零阶算法在样本复杂度和问题参数方面接近最优。基于此算法,我们还提出了一个估计的最小值的函数实现几乎尖锐的预言行为。我们将我们的结果与最先进的技术进行比较,突出了一些关键的改进。

英文摘要:

We study the problem of zero-order optimization of a strongly convex function. The goal is to find the minimizer of the function by a sequential exploration of its values, under measurement noise. We study the impact of higher order smoothness properties of the function on the optimization error and on the cumulative regret. To solve this problem we consider a randomized approximation of the projected gradient descent algorithm. The gradient is estimated by a randomized procedure involving two function evaluations and a smoothing kernel. We derive upper bounds for this algorithm both in the constrained and unconstrained settings and prove minimax lower bounds for any sequential search method. Our results imply that the zero-order algorithm is nearly optimal in terms of sample complexity and the problem parameters. Based on this algorithm, we also propose an estimator of the minimum value of the function achieving almost sharp oracle behavior. We compare our results with the state-of-the-art, highlighting a number of key improvements.

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。

↑