Fast and Extensible Online Multivariate Kernel Density Estimation
This work provides a more efficient and stable solution for real-time density estimation in streaming data applications, though it builds incrementally on existing online density estimation methods.
The paper tackles online multivariate kernel density estimation by presenting xokde++, which maintains Gaussian mixture models for data streams with improved computational efficiency and numerical robustness. The approach achieves up to 40 times faster speed and 90% less memory usage compared to state-of-the-art methods while maintaining comparable or better modeling quality.
We present xokde++, a state-of-the-art online kernel density estimation approach that maintains Gaussian mixture models input data streams. The approach follows state-of-the-art work on online density estimation, but was redesigned with computational efficiency, numerical robustness, and extensibility in mind. Our approach produces comparable or better results than the current state-of-the-art, while achieving significant computational performance gains and improved numerical stability. The use of diagonal covariance Gaussian kernels, which further improve performance and stability, at a small loss of modelling quality, is also explored. Our approach is up to 40 times faster, while requiring 90\% less memory than the closest state-of-the-art counterpart.