Passer à la navigation principale Passer à la recherche Passer au contenu principal

Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications

  • LTCI
  • Data and Ai Lab
  • Institut Polytechnique de Paris

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

5 Citations (Scopus)

Résumé

Motivated by a wide variety of applications, ranging from stochastic optimization to dimension reduction through variable selection, the problem of estimating gradients accurately is of crucial importance in statistics and learning theory. We consider here the classical regression setup, where a real valued square integrable r.v. Y is to be predicted upon observing a (possibly high dimensional) random vector X by means of a predictive function f(X) as accurately as possible in the mean-squared sense and study a nearest-neighbour-based pointwise estimate of the gradient of the optimal predictive function, the regression function m(x) = E[Y | X = x]. Under classical smoothness conditions combined with the assumption that the tails of Y − m(X) are sub-Gaussian, we prove nonasymptotic bounds improving upon those obtained for alternative estimation methods. Beyond the novel theoretical results established, several illustrative numerical experiments have been carried out. The latter provide strong empirical evidence that the estimation method proposed here performs very well for various statistical problems involving gradient estimation, namely dimensionality reduction, stochastic gradient descent optimization and disentanglement quantification.

langue originaleAnglais
Pages (de - à)532-540
Nombre de pages9
journalProceedings of Machine Learning Research
Volume130
étatPublié - 1 janv. 2021
Evénement24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 - Virtual, Online, États-Unis
Durée: 13 avr. 2021 → 15 avr. 2021

Empreinte digitale

Examiner les sujets de recherche de « Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation