arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1101.3501stat.MLmath.OCmath.STstat.TH
收藏

有效全局优化算法的收敛速度

Convergence rates of efficient global optimization algorithms

Adam D. Bull

摘要:

有效的全局优化是使用尽可能少的求值f(x)来最小化未知函数f的问题。它可以被看作是一个连续的武装土匪问题,无噪声数据和简单的遗憾。期望改进可能是解决这个问题的最流行的方法;该算法在实验中表现良好,但对其理论性质知之甚少。实现预期的改进需要选择高斯过程先验,这决定了相关的函数空间,即其再现核Hilbert空间(RKHS)。当先验是固定的,预期的改善是已知的RKHS中的任何函数的最小值收敛。我们首先提供收敛速度为这个过程。率是最佳的低平滑度的功能,我们修改算法,以达到最佳的利率平滑的功能。然而,对于从业者来说,这些结果有点误导。先验通常不保持固定,而是取决于从数据估计的参数。对于标准的估计,我们表明这个过程可能永远不会发现最小的f。然后,我们提出了替代估计,选择最小化常数的收敛速度,并显示这些估计保留了一个固定的先验的收敛速度。

英文摘要:

Efficient global optimization is the problem of minimizing an unknown function f, using as few evaluations f(x) as possible. It can be considered as a continuum-armed bandit problem, with noiseless data and simple regret. Expected improvement is perhaps the most popular method for solving this problem; the algorithm performs well in experiments, but little is known about its theoretical properties. Implementing expected improvement requires a choice of Gaussian process prior, which determines an associated space of functions, its reproducing-kernel Hilbert space (RKHS). When the prior is fixed, expected improvement is known to converge on the minimum of any function in the RKHS. We begin by providing convergence rates for this procedure. The rates are optimal for functions of low smoothness, and we modify the algorithm to attain optimal rates for smoother functions. For practitioners, however, these results are somewhat misleading. Priors are typically not held fixed, but depend on parameters estimated from the data. For standard estimators, we show this procedure may never discover the minimum of f. We then propose alternative estimators, chosen to minimize the constants in the rate of convergence, and show these estimators retain the convergence rates of a fixed prior.

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。

↑