Normalizing self-supervised learning for provably reliable Change Point Detection
This addresses the need for reliable CPD in real-world scenarios by providing a provably robust approach, though it is incremental as it builds on existing representation learning methods.
The paper tackles the problem of change point detection (CPD) by integrating representation learning with traditional techniques to overcome limitations like low expressive power and lack of theoretical reliability, resulting in a method that significantly outperforms state-of-the-art methods on three standard datasets.
Change point detection (CPD) methods aim to identify abrupt shifts in the distribution of input data streams. Accurate estimators for this task are crucial across various real-world scenarios. Yet, traditional unsupervised CPD techniques face significant limitations, often relying on strong assumptions or suffering from low expressive power due to inherent model simplicity. In contrast, representation learning methods overcome these drawbacks by offering flexibility and the ability to capture the full complexity of the data without imposing restrictive assumptions. However, these approaches are still emerging in the CPD field and lack robust theoretical foundations to ensure their reliability. Our work addresses this gap by integrating the expressive power of representation learning with the groundedness of traditional CPD techniques. We adopt spectral normalization (SN) for deep representation learning in CPD tasks and prove that the embeddings after SN are highly informative for CPD. Our method significantly outperforms current state-of-the-art methods during the comprehensive evaluation via three standard CPD datasets.