arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.13636cs.LGstat.ML
收藏

用权函数逼近目标分布

Approximating a Target Distribution using Weight Queries

Ben Gurion University(本·古里安大学)

Nadav Barak, Sivan Sabato

摘要:

我们考虑了一个新的挑战:近似的分布,没有能力从该分布中随机抽样。我们研究如何使用 * 权重查询 * 获得这样的近似。给定一些示例的数据集,权重查询将其中一个示例呈现给Oracle,该Oracle根据目标分布返回观察到与所呈现的示例类似的示例的概率。例如,该预言机可以表示对目标人群的数据库的查询计数,或者表示对返回与给定搜索匹配的结果的数量的搜索引擎的接口。我们提出了一个交互式算法,迭代地选择数据集的例子,并执行相应的权重查询。该算法使用有限数量的权重查询,根据目标分布找到近似权重的数据集的重新加权。我们推导出一个近似界的总变化之间的距离由算法找到的重新加权和最佳可实现的重新加权。我们的算法的灵感来自于UCB方法常见的多武装土匪问题,并结合了一个新的差异估计和贪婪的迭代过程。除了我们的理论保证,我们在实验中证明了所提出的算法在几个基线的优势。所提出的算法和所有实验的Python实现可以在https://github.com/Nadav-Barak/AWP上找到。

英文摘要:

We consider a novel challenge: approximating a distribution without the ability to randomly sample from that distribution. We study how such an approximation can be obtained using *weight queries*. Given some data set of examples, a weight query presents one of the examples to an oracle, which returns the probability, according to the target distribution, of observing examples similar to the presented example. This oracle can represent, for instance, counting queries to a database of the target population, or an interface to a search engine which returns the number of results that match a given search. We propose an interactive algorithm that iteratively selects data set examples and performs corresponding weight queries. The algorithm finds a reweighting of the data set that approximates the weights according to the target distribution, using a limited number of weight queries. We derive an approximation bound on the total variation distance between the reweighting found by the algorithm and the best achievable reweighting. Our algorithm takes inspiration from the UCB approach common in multi-armed bandits problems, and combines it with a new discrepancy estimator and a greedy iterative procedure. In addition to our theoretical guarantees, we demonstrate in experiments the advantages of the proposed algorithm over several baselines. A python implementation of the proposed algorithm and of all the experiments can be found at https://github.com/Nadav-Barak/AWP.

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。

↑