Skip to content
DraconiticResearch
Search Sources API
182,469 studies31 sourcesUpdated 47 min ago
PreprintCC BY 4.0arXiv

Adaptive minimax multivariate L1-deconvolution: harmonic-mean rates under noise filtering, and a 1-Wasserstein equivalence

  • Catia Scricciolo
Open at sourcePDFDOICite

Abstract

We study the multivariate convolution model with additive independent noise, multidimensional signal and noise, aiming to recover the signal's cumulative distribution function from contaminated observations. The noise is ordinary smooth with anisotropic regularity, and the signal belongs to an anisotropic Nikol'skii density class. We extend to the multivariate setting an approximate minimum L1-distance estimator based on integrated kernel density estimation, and establish matching upper and lower bounds for the L1-risk over anisotropic Nikol'skii classes. To our knowledge, this is the first minimax rate, not a sharpening of existing bounds. Although the lower-bound scheme is classical, the test-function construction is novel: it distinguishes no active component from at least one active component. The rate is governed by a censoring mechanism through the positive part, a noise filter in a harmonic-mean representation of the exponent. We further propose a fully data-driven, rate-adaptive procedure selecting an optimal bandwidth vector over the full Nikol'skii scale. On Nikol'skii product density classes, the L1-distance between cumulative distribution functions and the 1-Wasserstein distance share the same minimax rate, though not equivalent in general, via coordinate-wise decoupling of the 1-Wasserstein cost on product measures. These findings reveal a link between the two distances, whose full understanding remains an open question.

Related

  1. Equivalence between Strict Viscosity Solution and Viscosity Solution in the Wasserstein Space and Regular Extension of the Hamiltonian in L 2 ℙ
    Chloé Jimenez
    Journal of Convex AnalysisPeer-reviewedLicence not statedFull text1 citedGeneral mathematicsHAL
  2. Matrix equivalence to Smith normal form: new theoretical results for multivariate polynomial matrices
    Dong Lu, Yuanyuan Ruan, Dingkang Wang +1
    arXivPreprintarXiv licenceFull textAlgebra & number theoryarXiv
  3. Toscani-Fourier Distance on Probability Measures: Wasserstein Control, Topological Equivalence on Model Classes, and Duality
    Mehrdad Mohammadi
    arXivPreprintarXiv licenceFull textAnalysis & PDEsProbabilityarXiv
  4. Wasserstein Kernel Regression with Dependent Distribution-Valued Predictors: Local Recurrence, Joint Inference, and Multivariate Gaussian Geometry
    Wahiba Bouabsa, Fatimah Alshahrani
    MathematicsPeer-reviewedCC BY 4.0StatisticsCrossref
  5. Uniformly Improved Adaptive Filtering Procedures for Replicability Testing with FWER Control
    Ninh Tran
    arXivPreprintCC BY 4.0Full textStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{scricciolo2026adaptive,
  title = {{Adaptive minimax multivariate \(L^1\)-deconvolution: harmonic-mean rates under noise filtering, and a \(1\)-Wasserstein equivalence}},
  author = {Catia Scricciolo},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.11760},
  eprint = {2610.11760},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.11760},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Adaptive minimax multivariate L^1-deconvolution: harmonic-mean rates under noise filtering, and a 1-Wasserstein equivalence
AU  - Catia Scricciolo
PY  - 2026
DA  - 2026/10/08
PB  - arXiv
DO  - 10.48550/arxiv.2610.11760
UR  - https://arxiv.org/abs/2610.11760
AB  - We study the multivariate convolution model with additive independent noise, multidimensional signal and noise, aiming to recover the signal's cumulative distribution function from contaminated observations. The noise is ordinary smooth with anisotropic regularity, and the signal belongs to an anisotropic Nikol'skii density class. We extend to the multivariate setting an approximate minimum L^1-distance estimator based on integrated kernel density estimation, and establish matching upper and lower bounds for the L^1-risk over anisotropic Nikol'skii classes. To our knowledge, this is the first minimax rate, not a sharpening of existing bounds. Although the lower-bound scheme is classical, the test-function construction is novel: it distinguishes no active component from at least one active component. The rate is governed by a censoring mechanism through the positive part, a noise filter in a harmonic-mean representation of the exponent. We further propose a fully data-driven, rate-adaptive procedure selecting an optimal bandwidth vector over the full Nikol'skii scale. On Nikol'skii product density classes, the L^1-distance between cumulative distribution functions and the 1-Wasserstein distance share the same minimax rate, though not equivalent in general, via coordinate-wise decoupling of the 1-Wasserstein cost on product measures. These findings reveal a link between the two distances, whose full understanding remains an open question.
ER  -