TY - GEN
T1 - Regularized Modal Regression on Markov-Dependent Observations
T2 - 36th AAAI Conference on Artificial Intelligence, AAAI 2022
AU - Gong, Tieliang
AU - Dong, Yuxin
AU - Chen, Hong
AU - Feng, Wei
AU - Dong, Bo
AU - Li, Chen
N1 - Publisher Copyright:
Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2022/6/30
Y1 - 2022/6/30
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85147732737
U2 - 10.1609/aaai.v36i6.20627
DO - 10.1609/aaai.v36i6.20627
M3 - 会议稿件
AN - SCOPUS:85147732737
T3 - Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
SP - 6721
EP - 6728
BT - AAAI-22 Technical Tracks 6
PB - Association for the Advancement of Artificial Intelligence
Y2 - 22 February 2022 through 1 March 2022
ER -