Skip to main navigation Skip to search Skip to main content

Regularized Modal Regression on Markov-Dependent Observations: A Theoretical Assessment

  • Key Lab of the Ministry of Education for Process Control and Efficiency Egineering
  • Xi'an Jiaotong University
  • Huazhong Agricultural University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Modal regression, a widely used regression protocol, has been extensively investigated in statistical and machine learning communities due to its robustness to outliers and heavy-tailed noises. Understanding modal regression’s theoretical behavior can be fundamental in learning theory. Despite significant progress in characterizing its statistical property, the majority of the results are based on the assumption that samples are independent and identical distributed (i.i.d.), which is too restrictive for real-world applications. This paper concerns the statistical property of regularized modal regression (RMR) within an important dependence structure - Markov dependent. Specifically, we establish the upper bound for RMR estimator under moderate conditions and give an explicit learning rate. Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of underlying Markov chain. This result shed a new light on characterizing the theoretical underpinning for robust regression.

Original languageEnglish
Title of host publicationAAAI-22 Technical Tracks 6
PublisherAssociation for the Advancement of Artificial Intelligence
Pages6721-6728
Number of pages8
ISBN (Electronic)1577358767, 9781577358763
DOIs
StatePublished - 30 Jun 2022
Event36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
Duration: 22 Feb 2022 → 1 Mar 2022

Publication series

NameProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
Volume36

Conference

Conference36th AAAI Conference on Artificial Intelligence, AAAI 2022
CityVirtual, Online
Period22/02/22 → 1/03/22

Fingerprint

Dive into the research topics of 'Regularized Modal Regression on Markov-Dependent Observations: A Theoretical Assessment'. Together they form a unique fingerprint.

Cite this