Kernel density estimation via diffusion

Abstract

We present a new adaptive kernel density estimator based on linear diffusion processes. The proposed estimator builds on existing ideas for adaptive smoothing by incorporating information from a pilot density estimate. In addition, we propose a new plug-in bandwidth selection method that is free from the arbitrary normal reference rules used by existing methods. We present simulation examples in which the proposed approach outperforms existing methods in terms of accuracy and reliability.

Published in at http://dx.doi.org/10.1214/10-AOS799 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (80)

• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• GetDist: a Python package for analysing Monte Carlo samples
• Low-Mass Dark Matter Search with CDMSlite
• Generative Models for Functional Data using Phase and Amplitude Separation
• Kernel density estimation based sampling for imbalanced class distribution
• Inferring broken detailed balance in the absence of observable currents
• Evaluating stationarity via change-point alternatives with applications to fMRI data
• Pulsar Timing Array Based Search for Supermassive Black Hole Binaries in the Square Kilometer Array Era
• Tomography of photon-number resolving continuous-output detectors
• An improved understanding of the roles of atomic processes and power balance in divertor target ion current loss during detachment
• An information theoretic framework for classifying exoplanetary system architectures
• Metal-enriched halo gas across galaxy overdensities over the last 10 billion years
• Deep learning and Bayesian inference of gravitational-wave populations: Hierarchical black-hole mergers
• Topology Density Map for Urban Data Visualization and Analysis
• Alkali-silica reaction products and cracks: X-ray micro-tomography-based analysis of their spatial-temporal evolution at a mesoscale
• A Look into Chaos Detection through Topological Data Analysis
• Efficient Statistically Accurate Algorithms for the Fokker-Planck Equation in Large Dimensions
• A novel hydrogenic spectroscopic technique for inferring the role of plasma-molecule interaction on power and particle balance during detached conditions
• Motor skill learning by increasing the movement planning horizon
• Statistical Simulator for the Engine Knock
• Iterative Estimation of Solutions to Noisy Nonlinear Operator Equations in Nonparametric Instrumental Regression
• GINNs: Graph-Informed Neural Networks for Multiscale Physics
• Robust period estimation using mutual information for multi-band light curves in the synoptic survey era
• A Cooperative Bayesian Nonparametric Framework for Primary User Activity Monitoring in Cognitive Radio Network
• Particle Density Estimation with Grid-Projected Adaptive Kernels
• Determining the core radio luminosity function of radio AGNs via copula
• Data-driven closures for stochastic dynamical systems
• Novel inferences of ionisation & recombination for particle/power balance during detached discharges using deuterium Balmer line spectroscopy
• Hierarchical clustering that takes advantage of both density-peak and density-connectivity
• MCR-TRGB: A Multiwavelength-Covariant, Robust Tip of the Red Giant Branch Measurement Method
• Non-parametric Kernel-Based Estimation of Probability Distributions for Precipitation Modeling
• Nonlinear softening as a predictive precursor to climate tipping
• Statistical Characteristics of Driver Acceleration Behavior and Its Probability Model
• Maximum-likelihood estimation of lithospheric flexural rigidity, initial-loading fraction, and load correlation, under isotropy
• Conditional Gaussian Nonlinear System: a Fast Preconditioner and a Cheap Surrogate Model For Complex Nonlinear Systems
• On Reciprocity in Physically Consistent TDD Systems with Coupled Antennas
• Emission-line diagnostics of HII regions using conditional Invertible Neural Networks
• Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning
• Extending the frequency reach of pulsar timing array based gravitational wave search without high cadence observations
• Mutual Information for Explainable Deep Learning of Multiscale Systems
• Data-Based Optimal Bandwidth for Kernel Density Estimation of Statistical Samples
• Bayesian Regression and Classification Using Gaussian Process Priors Indexed by Probability Density Functions
• Kernel Density Estimation with Linked Boundary Conditions
• S2D2: Small-scale Significant substructure DBSCAN Detection I. NESTs detection in 2D star-forming regions
• Density Estimation with Distribution Element Trees
• Three-dimensional atomically-resolved analytical imaging with a field ion microscope
• A flexible method for estimating luminosity functions via Kernel Density Estimation
• Inference of epidemiological parameters from household stratified data
• Riemannian Gaussian distributions, random matrix ensembles and diffusion kernels
• Elementary excitations and the phase transition in the bimodal Ising spin glass model
• fBLS -- a fast-folding BLS algorithm
• Consistent second-order discrete kernel smoothing using dispersed Conway-Maxwell-Poisson kernels
• A binary origin for the first isolated stellar-mass black hole detected with astrometric microlensing
• Quantifying model uncertainty for the observed non-Gaussian data by the Hellinger distance
• Cosmic star formation history with tomographic cosmic infrared background-galaxy cross-correlation
• Constraints on Tidal Quality Factor in Kepler Eclipsing Binaries using Tidal Synchronization: A Frequency-Dependent Approach
• Quasi-symmetries in complex networks: a dynamical model approach
• Adaptive Graph Integration for Cross-Domain Recommendation via Heterogeneous Graph Coordinators
• Minimum Local Distance Density Estimation
• Power Network Uniqueness and Synchronization Stability from a Higher-order Structure Perspective
• (Un)Conditional Sample Generation Based on Distribution Element Trees
• Statistical significance of meteorite-asteroid pairs using geocentric parameters
• Fast, Convexified Stochastic Optimal Open-Loop Control For Linear Systems Using Empirical Characteristic Functions
• Double-slit interference with charged particles. Density matrices and decoherence from time-dependent quantum Monte Carlo
• Generative modeling of time-dependent densities via optimal transport and projection pursuit
• A diffusion equation for the density of the ratio of two jointly distributed Gaussian variables and the numerical inversion of Laplace transform
• Predicting Magnetic Janus Particle Assembly with Differential Evolution Algorithm
• Non-parametric kernel density estimation of magnitude distribution for the analysis of seismic hazard posed by anthropogenic seismicity
• The characteristics of the meandering effect in a stratified wake
• Reduction of multivariate mixtures and its applications
• A new adaptive local polynomial density estimation procedure on complicated domains
• Piecewise polynomial approximation of probability density functions with application to uncertainty quantification for stochastic PDEs
• Quantitative Image-Based Validation Framework for Assessing Global Coronal Magnetic Field Models
• SimOutUtils - Utilities for analyzing time series simulation output
• A stochastic density matrix approach to approximation of probability distributions and its application to nonlinear systems
• A flexible method for estimating luminosity functions via Kernel Density Estimation -- II. Generalization and Python implementation
• Nonlinear Modal Interval Regression for Bivariate Data Analysis
• Data-driven Closures & Assimilation for Stiff Multiscale Random Dynamics
• Inferring entropy production rate from partially observed Langevin dynamics under coarse-graining
• Anytime Parallel Tempering