Breaking the curse of dimensionality in structured density estimation
Keywords: nonparametric statistics, density estimation, graphical models, sample complexity, curse of dimensionality
TL;DR: This work presents a new graphical quantity and shows that, when one assumes the Markov property over this graph, it leads to much faster rates for nonparametric density estimation.
Abstract: We consider the problem of estimating a structured multivariate density, subject to Markov conditions implied by an undirected graph. In the worst case, without Markovian assumptions, this problem suffers from the curse of dimensionality. Our main result shows how the curse of dimensionality can be avoided or greatly alleviated under the Markov property, and applies to arbitrary graphs. While existing results along these lines focus on sparsity or manifold assumptions, we introduce a new graphical quantity called ``graph resilience'' and show that it dictates the optimal sample complexity. Surprisingly, although one might expect the sample complexity of this problem to scale with local graph parameters such as the degree, this turns out not to be the case. Through explicit examples, we compute uniform deviation bounds and illustrate how the curse of dimensionality in density estimation can thus be circumvented. Notable examples where the rate improves substantially include sequential, hierarchical, and spatial data.
Primary Area: Learning theory
Submission Number: 7579
Loading