Kernel Density Machines
By: Damir Filipovic, Paul Schneider
Potential Business Impact:
Helps computers learn patterns from messy data.
We introduce kernel density machines (KDM), a nonparametric estimator of a Radon--Nikodym derivative, based on reproducing kernel Hilbert spaces. KDM applies to general probability measures on countably generated measurable spaces under minimal assumptions. For computational efficiency, we incorporate a low-rank approximation with precisely controlled error that grants scalability to large-sample settings. We provide rigorous theoretical guarantees, including asymptotic consistency, a functional central limit theorem, and finite-sample error bounds, establishing a strong foundation for practical use. Empirical results based on simulated and real data demonstrate the efficacy and precision of KDM.
Similar Papers
Non-parametric kernel density estimation of magnitude distribution for the analysis of seismic hazard posed by anthropogenic seismicity
Geophysics
Predicts earthquakes more accurately using new math.
SD-KDE: Score-Debiased Kernel Density Estimation
Machine Learning (CS)
Improves how computers guess data patterns.
Kernel K-means clustering of distributional data
Machine Learning (Stat)
Groups similar data patterns together automatically.