Variational Information Bottleneck with Gaussian Processes for Time-Series Classification

Itamar Efrati, Shai Fine

Abstract: Time series classification problems are prevalent across various domains, often characterized by intra-series relationships within features, and inter-series relationships between the same features over time. Developing a generalized model capable of capturing these intricate properties poses a considerable challenge. In this paper, we introduce an innovative approach termed Gaussian Process Variational Information Bottleneck (GP-VIB). This model is designed as an end-to-end system, with a primary focus on acquiring a concise representation of the initial sequence. It aims to retain essential information vital for accurate classification. Through our experiments, we illustrate that the proposed GP-VIB model outperforms existing methods on renowned benchmark datasets.