Scalable Empirical Dynamic Modeling With Parallel Computing and Approximate k-NN Search

K Takahashi and K Ichikawa and J Park and GM Pao, IEEE ACCESS, 11, 68171-68183 (2023).

DOI: 10.1109/ACCESS.2023.3289836

Empirical Dynamic Modeling (EDM) is a mathematical framework for modeling and predicting non-linear time series data. Although EDM is increasingly adopted in various research fields, its application to large-scale data has been limited due to its high computational cost. This article presents kEDM, a high-performance implementation of EDM for analyzing large-scale time series datasets. kEDM adopts the Kokkos performance-portable programming model to efficiently run on both CPU and GPU while sharing a single code base. We also conduct hardware- specific optimization of performance-critical kernels. kEDM achieved up to 6.58 x speedup in pairwise causal inference of real-world biology datasets compared to an existing EDM implementation. Furthermore, we integrate multiple approximate k-NN search algorithms into EDM to enable the analysis of extremely large datasets that were intractable with conventional EDM based on exhaustive k-NN search. EDM-based time series forecast enhanced with approximate k-NN search demonstrated up to 790x speedup compared to conventional Simplex projection with less than 1% increase in MAPE.

Return to Publications page