Learning non-Gaussian multi-index model via second-order Stein's method

Zhuoran Yang, Krishna Balasubramanian, Zhaoran Wang, Han Liu

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

We consider estimating the parametric components of semiparametric multi-index models in high dimensions. To bypass the requirements of Gaussianity or elliptical symmetry of covariates in existing methods, we propose to leverage a second-order Stein's method with score function-based corrections. We prove that our estimator achieves a near-optimal statistical rate of convergence even when the score function or the response variable is heavy-tailed. To establish the key concentration results, we develop a data-driven truncation argument that may be of independent interest. We supplement our theoretical findings with simulations.

Original languageEnglish (US)
Pages (from-to)6098-6107
Number of pages10
JournalAdvances in Neural Information Processing Systems
Volume2017-December
StatePublished - 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Learning non-Gaussian multi-index model via second-order Stein's method'. Together they form a unique fingerprint.

Cite this