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 2009.02539stat.MLcs.ITcs.LGmath.IT
收藏

亚线性 regrets 界限的未知搜索空间中的贝叶斯优化

Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces

Applied Artificial Intelligence Institute(应用人工智能研究所);Deakin University(德金大学)

Hung Tran-The, Sunil Gupta, Santu Rana, Huong Ha, Svetha Venkatesh

AI总结:

本文提出了一种扩展搜索空间的贝叶斯优化算法,通过超调和级数控制扩展率,实现亚线性 regrets 界限,并在高维空间中验证了其优越性。

摘要:

贝叶斯优化是一种用于高效优化昂贵黑盒函数的流行方法。传统上,BO假设搜索空间是已知的。然而,在许多问题中,这一假设不成立。为此,我们提出了一种新的BO算法,通过迭代扩展(并移位)搜索空间,基于超谐级数控制扩展率。进一步,我们提出了一种扩展到高维空间的算法变体。我们理论证明,对于这两种算法,累积 regrets 增长率呈亚线性。我们的合成和现实优化任务实验展示了我们的算法在未知搜索空间中的贝叶斯优化中优于当前最先进方法。

英文摘要:

Bayesian optimisation is a popular method for efficient optimisation of expensive black-box functions. Traditionally, BO assumes that the search space is known. However, in many problems, this assumption does not hold. To this end, we propose a novel BO algorithm which expands (and shifts) the search space over iterations based on controlling the expansion rate thought a hyperharmonic series. Further, we propose another variant of our algorithm that scales to high dimensions. We show theoretically that for both our algorithms, the cumulative regret grows at sub-linear rates. Our experiments with synthetic and real-world optimisation tasks demonstrate the superiority of our algorithms over the current state-of-the-art methods for Bayesian optimisation in unknown search space.

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。

↑