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 2410.04037stat.MLcs.LG
收藏

得分匹配是否适用于点过程估计?

Is Score Matching Suitable for Estimating Point Processes?

Renmin University of China(中国人民大学);University of Technology Sydney(悉尼科技大学)

Haoqun Cao, Zizhuo Meng, Tianjun Ke, Feng Zhou

AI总结:

针对现有得分匹配估计器在通用点过程估计中失效的问题,提出加权得分匹配估计器,证明其一致性与收敛速率,实验验证其有效性并开源代码。

摘要:

得分匹配估计器近年来受到广泛关注,部分原因在于其无需计算归一化常数的积分,从而解决了最大似然估计(MLE)中的计算难题。已有部分研究提出了针对点过程的得分匹配估计器。但本研究表明,这些工作提出的估计器存在不完备性,仅适用于特定问题,在更通用的点过程场景下会失效。为解决该问题,本研究将加权得分匹配估计器引入点过程领域。理论上,我们证明了该估计器的一致性,并推导了其收敛速率。实验结果显示,我们的估计器在合成数据上能准确估计模型参数,在真实数据上的结果与MLE一致;相比之下,现有得分匹配估计器无法有效发挥作用。代码公开于https://github.com/KenCao2007/WSM_TPP。

英文摘要:

Score matching estimators have gained widespread attention in recent years partly because they are free from calculating the integral of normalizing constant, thereby addressing the computational challenges in maximum likelihood estimation (MLE). Some existing works have proposed score matching estimators for point processes. However, this work demonstrates that the incompleteness of the estimators proposed in those works renders them applicable only to specific problems, and they fail for more general point processes. To address this issue, this work introduces the weighted score matching estimator to point processes. Theoretically, we prove the consistency of our estimator and establish its rate of convergence. Experimental results indicate that our estimator accurately estimates model parameters on synthetic data and yields results consistent with MLE on real data. In contrast, existing score matching estimators fail to perform effectively. Codes are publicly available at \url{https://github.com/KenCao2007/WSM_TPP}.

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。

↑