Unlabeled Data Help in Graph-Based Semi-Supervised Learning: A Bayesian Nonparametrics Perspective

被引：0
作者：
Sanz-Alonso, Daniel [1 ]
Yang, Ruiyi [2 ]
机构：
[1] Univ Chicago, Dept Stat, Chicago, IL 60637 USA
[2] Univ Chicago, Comm Comp & Appl Math, Chicago, IL 60637 USA
来源：
JOURNAL OF MACHINE LEARNING RESEARCH | 2022年 / 23卷
关键词：
semi-supervised learning; graph-Laplacians; Bayesian nonparametrics; Gaus-sian fields on manifold; POSTERIOR DISTRIBUTIONS; CONVERGENCE-RATES; LAPLACIAN;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper we analyze the graph-based approach to semi-supervised learning under a manifold assumption. We adopt a Bayesian perspective and demonstrate that, for a suitable choice of prior constructed with sufficiently many unlabeled data, the posterior contracts around the truth at a rate that is minimax optimal up to a logarithmic factor. Our theory covers both regression and classification.
引用
收藏
页数：28
相关论文
共 52 条
[1]  
[Anonymous], 2010, P 2010 C EMP METH NA
[2]  
[Anonymous], 1992, Monogr. Math.
[3]  
[Anonymous], 2008, Advances in Neural Information Processing Systems
[4]   Regularization and semi-supervised learning on large graphs [J].
Belkin, M ;
Matveeva, I ;
Niyogi, P .
LEARNING THEORY, PROCEEDINGS, 2004, 3120 :624-638
[5]   Semi-supervised learning on Riemannian manifolds [J].
Belkin, M ;
Niyogi, P .
MACHINE LEARNING, 2004, 56 (1-3) :209-239
[6]   Posterior consistency of semi-supervised regression on graphs [J].
Bertozzi, Andrea L. ;
Hosseini, Bamdad ;
Li, Hao ;
Miller, Kevin ;
Stuart, Andrew M. .
INVERSE PROBLEMS, 2021, 37 (10)
[7]  
Bickel P. J., 2007, Lecture Notes-Monograph Series, V54, P177
[8]  
Calder J., 2020, ARXIV200602765
[9]   LIPSCHITZ REGULARITY OF GRAPH LAPLACIANS ON RANDOM DATA CLOUDS [J].
Calder, Jeff ;
Trillos, Nicolas Garcia ;
Lewicka, Marta .
SIAM JOURNAL ON MATHEMATICAL ANALYSIS, 2022, 54 (01) :1169-1222
[10]  
Calder Jeff, 2022, APPL COMPUTATIONAL H
123456