Active Learning for Level Set Estimation
Active Learning for Level Set Estimation
复制标题
水平集估计的主动学习
DOI：
10.3929/ethz-a-009767767
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Andreas Krause
中科院分区：
文献类型：
--
作者：
Alkis Gotovos;N. Casati;Gregory Hitz;Andreas Krause
许多信息收集问题需要确定点的集合，对于这些点，未知函数的值高于或低于某个给定的阈值水平。我们将此任务形式化为具有顺序测量的分类问题，其中未知函数被建模为来自高斯过程（GP）的样本。我们提出了LSE，一个算法，指导采样和分类的基础上GP派生的置信区间，并提供理论保证其样本的复杂性。此外，我们将LSE及其理论扩展到两个更自然的设置：（1）阈值水平被隐式定义为目标函数（未知）最大值的百分比，以及（2）批量选择样本。我们评估了我们提出的方法的有效性，对两个问题的实际利益，即自主监测藻类种群在湖泊环境和地理定位网络延迟。
Many information gathering problems require determining the set of points, for which an unknown function takes value above or below some given threshold level. We formalize this task as a classification problem with sequential measurements, where the unknown function is modeled as a sample from a Gaussian process (GP). We propose LSE, an algorithm that guides both sampling and classification based on GP-derived confidence bounds, and provide theoretical guarantees about its sample complexity. Furthermore, we extend LSE and its theory to two more natural settings: (1) where the threshold level is implicitly defined as a percentage of the (unknown) maximum of the target function and (2) where samples are selected in batches. We evaluate the effectiveness of our proposed methods on two problems of practical interest, namely autonomous monitoring of algal populations in a lake environment and geolocating network latency.