On minimax density estimation via measure transport
- URL: http://arxiv.org/abs/2207.10231v1
- Date: Wed, 20 Jul 2022 23:56:00 GMT
- Title: On minimax density estimation via measure transport
- Authors: Sven Wang, Youssef Marzouk
- Abstract summary: We study the convergence properties of nonparametric density estimators based on measure transport.
We show that penalized and unpenalized versions of such estimators achieve minimax optimal convergence rates over H"older classes of densities.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We study the convergence properties, in Hellinger and related distances, of
nonparametric density estimators based on measure transport. These estimators
represent the measure of interest as the pushforward of a chosen reference
distribution under a transport map, where the map is chosen via a maximum
likelihood objective (equivalently, minimizing an empirical Kullback-Leibler
loss) or a penalized version thereof. We establish concentration inequalities
for a general class of penalized measure transport estimators, by combining
techniques from M-estimation with analytical properties of the transport-based
density representation. We then demonstrate the implications of our theory for
the case of triangular Knothe-Rosenblatt (KR) transports on the $d$-dimensional
unit cube, and show that both penalized and unpenalized versions of such
estimators achieve minimax optimal convergence rates over H\"older classes of
densities. Specifically, we establish optimal rates for unpenalized
nonparametric maximum likelihood estimation over bounded H\"older-type balls,
and then for certain Sobolev-penalized estimators and sieved wavelet
estimators.
Related papers
- Multivariate root-n-consistent smoothing parameter free matching estimators and estimators of inverse density weighted expectations [51.000851088730684]
We develop novel modifications of nearest-neighbor and matching estimators which converge at the parametric $sqrt n $-rate.
We stress that our estimators do not involve nonparametric function estimators and in particular do not rely on sample-size dependent parameters smoothing.
arXiv Detail & Related papers (2024-07-11T13:28:34Z) - Conditional Optimal Transport on Function Spaces [53.9025059364831]
We develop a theory of constrained optimal transport problems that describe block-triangular Monge maps.
This generalizes the theory of optimal triangular transport to separable infinite-dimensional function spaces with general cost functions.
We present numerical experiments that demonstrate the computational applicability of our theoretical results for amortized and likelihood-free inference of functional parameters.
arXiv Detail & Related papers (2023-11-09T18:44:42Z) - Minimax estimation of discontinuous optimal transport maps: The
semi-discrete case [14.333765302506658]
We consider the problem of estimating the optimal transport map between two probability distributions, $P$ and $Q$ in $mathbb Rd$.
We show that an estimator based on entropic optimal transport converges at the minimax-optimal rate $n-1/2$, independent of dimension.
arXiv Detail & Related papers (2023-01-26T18:41:38Z) - Near-optimal estimation of smooth transport maps with kernel
sums-of-squares [81.02564078640275]
Under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error upper bounds.
The object of interest for applications such as generative modeling is the underlying optimal transport map.
We propose the first tractable algorithm for which the statistical $L2$ error on the maps nearly matches the existing minimax lower-bounds for smooth map estimation.
arXiv Detail & Related papers (2021-12-03T13:45:36Z) - Plugin Estimation of Smooth Optimal Transport Maps [25.23336043463205]
We show that a number of natural estimators for the optimal transport map between two distributions are minimax optimal.
Our work provides new bounds on the risk of corresponding plugin estimators for the quadratic Wasserstein distance.
arXiv Detail & Related papers (2021-07-26T17:58:48Z) - Rates of Estimation of Optimal Transport Maps using Plug-in Estimators
via Barycentric Projections [0.0]
We provide a comprehensive analysis of the rates of convergences for general plug-in estimators defined via barycentric projections.
Our main contribution is a new stability estimate for barycentric projections which proceeds under minimal smoothness assumptions.
We illustrate the usefulness of this stability estimate by first providing rates of convergence for the natural discrete-discrete and semi-discrete estimators of optimal transport maps.
arXiv Detail & Related papers (2021-07-04T19:50:20Z) - On Projection Robust Optimal Transport: Sample Complexity and Model
Misspecification [101.0377583883137]
Projection robust (PR) OT seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected.
Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances.
Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces.
arXiv Detail & Related papers (2020-06-22T14:35:33Z) - Nonparametric Estimation of the Fisher Information and Its Applications [82.00720226775964]
This paper considers the problem of estimation of the Fisher information for location from a random sample of size $n$.
An estimator proposed by Bhattacharya is revisited and improved convergence rates are derived.
A new estimator, termed a clipped estimator, is proposed.
arXiv Detail & Related papers (2020-05-07T17:21:56Z) - Robust Density Estimation under Besov IPM Losses [10.079698681921672]
We study minimax convergence rates of nonparametric density estimation in the Huber contamination model.
We show that a re-scaled thresholding wavelet series estimator achieves minimax optimal convergence rates under a wide variety of losses.
arXiv Detail & Related papers (2020-04-18T11:30:35Z) - Minimax Optimal Estimation of KL Divergence for Continuous Distributions [56.29748742084386]
Esting Kullback-Leibler divergence from identical and independently distributed samples is an important problem in various domains.
One simple and effective estimator is based on the k nearest neighbor between these samples.
arXiv Detail & Related papers (2020-02-26T16:37:37Z) - Statistical Optimal Transport posed as Learning Kernel Embedding [0.0]
This work takes the novel approach of posing statistical Optimal Transport (OT) as that of learning the transport plan's kernel mean embedding from sample based estimates of marginal embeddings.
A key result is that, under very mild conditions, $epsilon$-optimal recovery of the transport plan as well as the Barycentric-projection based transport map is possible with a sample complexity that is completely dimension-free.
arXiv Detail & Related papers (2020-02-08T14:58:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.