Density Estimation via Binless Multidimensional Integration

Abstract

We introduce the Binless Multidimensional Thermodynamic Integration (BMTI) method for nonparametric, robust, and data-efficient density estimation. BMTI estimates the logarithm of the density by initially computing log-density differences between neighbouring data points. Subsequently, such differences are integrated, weighted by their associated uncertainties, using a maximum-likelihood formulation. This procedure can be seen as an extension to a multidimensional setting of the thermodynamic integration, a technique developed in statistical physics. The method leverages the manifold hypothesis, estimating quantities within the intrinsic data manifold without defining an explicit coordinate map. It does not rely on any binning or space partitioning, but rather on the construction of a neighbourhood graph based on an adaptive bandwidth selection procedure. BMTI mitigates the limitations commonly associated with traditional nonparametric density estimators, effectively reconstructing smooth profiles even in high-dimensional embedding spaces. The method is tested on a variety of complex synthetic high-dimensional datasets, where it is shown to outperform traditional estimators, and is benchmarked on realistic datasets from the chemical physics literature.

References in corpus (16)

• Deep Learning in Neural Networks: An Overview
• Escaping free-energy minima
• Normalizing Flows: An Introduction and Review of Current Methods
• Estimating the intrinsic dimension of datasets by a minimal neighborhood information
• Enhanced sampling methods for molecular dynamics simulations
• Single-Sweep Methods for Free Energy Calculations
• Roundtrip: A Deep Generative Neural Density Estimator
• Scikit-dimension: a Python package for intrinsic dimension estimation
• Automatic topography of high-dimensional data sets by non-parametric Density Peak clustering
• normflows: A PyTorch Package for Normalizing Flows
• DADApy: Distance-based Analysis of DAta-manifolds in Python
• Time-independent free energies from metadynamics via Mean Force Integration
• Intrinsic dimension estimation for locally undersampled data
• Intrinsic dimension estimation for discrete metrics
• The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning
• An Efficient and Continuous Voronoi Density Estimator