Penalty Learning for Optimal Partitioning through Deep Learning Techniques

Abstract Changepoint detection or partitioning, a technique for identifying significant shifts within data sequences, is crucial in various fields such as finance, genomics, medicine, etc. Dynamic programming changepoint detection algorithms are employed to effectively identify the locations of changepoints within a sequence, which rely on a penalty parameter to regulate the number of changepoints. To estimate this penalty parameter, previous work uses simple models such as linear or tree-based models. This study introduces a novel deep learning method for predicting this penalty parameter, leading to demonstrably improved changepoint detection accuracy on large benchmark supervised labeled datasets compared to previous methods.