Access the full text.
Sign up today, get DeepDyve free for 14 days.
O. Chapelle, Bernhard Schlkopf, A. Zien (2006)
Semi-Supervised LearningIEEE Transactions on Neural Networks, 20
S. Haykin, B. Kosko (2001)
GradientBased Learning Applied to Document Recognition
Matthias Hein, Jean-Yves Audibert (2005)
Intrinsic dimensionality estimation of submanifolds in RdProceedings of the 22nd international conference on Machine learning
D. Spielman, S. Teng (2003)
Nearly-linear time algorithms for graph partitioning, graph sparsification, and solving linear systemsArXiv, cs.DS/0310051
R. Ando, Tong Zhang (2006)
Learning on Graph with Laplacian Regularization
Yann LeCun, L. Bottou, Yoshua Bengio, P. Haffner (1998)
Gradient-based learning applied to document recognitionProc. IEEE, 86
N. Trillos, D. Slepčev, J. Brecht, T. Laurent, X. Bresson (2014)
Consistency of Cheeger and Ratio Graph CutsJ. Mach. Learn. Res., 17
Nicolás Trillos, D. Slepčev (2014)
Continuum Limit of Total Variation on Point CloudsArchive for Rational Mechanics and Analysis, 220
F. Santambrogio (2015)
Optimal Transport for Applied Mathematicians
D. Bartuschat (2007)
Algebraic Multigrid
M. Bardi, I. Capuzzo-Dolcetta (1997)
Optimal Control and Viscosity Solutions of Hamilton-Jacobi-Bellman Equations
G. Wolansky (2021)
Optimal Transport
A Braides (2002)
$$\Gamma $$ Γ -Convergence for Beginners. Oxford Lecture Series in Mathematics and Its Applications
G Maso (1993)
An introduction to $$\Gamma $$ Γ -Convergence. Progress in Nonlinear Differential Equations and Their Applications
A. Brandt, O. Livne (2011)
Multigrid Techniques: 1984 Guide with Applications to Fluid Dynamics, Revised Edition
A. Greenbaum (1997)
Iterative methods for solving linear systems, 17
G. Leoni (2009)
A First Course in Sobolev Spaces
Bin Xu, Jiajun Bu, Chun Chen, Deng Cai, Xiaofei He, W. Liu, Jiebo Luo (2011)
Efficient manifold ranking for image retrievalProceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
Jingrui He, Mingjing Li, HongJiang Zhang, Hanghang Tong, Changshui Zhang (2006)
Generalized Manifold-Ranking-Based Image RetrievalIEEE Transactions on Image Processing, 15
A. Singer (2006)
From graph to manifold Laplacian: The convergence rateApplied and Computational Harmonic Analysis, 21
J. Calder (2017)
The game theoretic p-Laplacian and semi-supervised learning with few labelsNonlinearity, 32
Zuoqiang Shi, S. Osher, Wei Zhu (2017)
Weighted Nonlocal Laplacian on Interpolation from Sparse DataJournal of Scientific Computing, 73
Jose Costa, A. Hero (2006)
Determining Intrinsic Dimension and Entropy of High-Dimensional Shape Spaces
M Thorpe, S Park, S Kolouri, GK Rohde, D Slepčev (2017)
A transportation $$L^p$$ L p distance for signal analysisJ. Math. Imaging Vis., 59
J. Calder (2017)
Consistency of Lipschitz learning with infinite unlabeled data and finite labeled dataArXiv, abs/1710.10364
Andrea Braides (2002)
Γ-convergence for beginners
M. Belkin, P. Niyogi (2002)
Using manifold structure for partially labelled classification
Matthew Thorpe, Serim Park, Soheil Kolouri, G. Rohde, D. Slepčev (2016)
A Transportation Lp\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L^p$$\end{document} Distance for Signal AnalysisJournal of Mathematical Imaging and Vision, 59
N. Trillos, Moritz Gerlach, Matthias Hein, D. Slepčev (2018)
Error Estimates for Spectral Convergence of the Graph Laplacian on Random Geometric Graphs Toward the Laplace–Beltrami OperatorFoundations of Computational Mathematics, 20
M. Talagrand (2021)
Upper and Lower Bounds for Stochastic ProcessesErgebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A Series of Modern Surveys in Mathematics
D. Gilbarg, N. Trudinger (1977)
Elliptic Partial Differential Equa-tions of Second Order
Chuan Yang, L. Zhang, Huchuan Lu, Xiang Ruan, Ming-Hsuan Yang (2013)
Saliency Detection via Graph-Based Manifold Ranking2013 IEEE Conference on Computer Vision and Pattern Recognition
Morteza Alamgir, U. Luxburg (2011)
Phase transition in the family of p-resistances
Jingrui He, Mingjing Li, HongJiang Zhang, Hanghang Tong, Changshui Zhang (2004)
Manifold-ranking based image retrieval
Xiaojin Zhu, Zoubin Ghahramani, J. Lafferty (2003)
Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions
Dengyong Zhou, O. Bousquet, T. Lal, J. Weston, B. Scholkopf (2003)
Learning with Local and Global Consistency
A Brandt, OE Livne (2011)
Multigrid Techniques: 1984 Guide with Applications to Fluid Dynamics
Nicolás Trillos, D. Slepčev (2015)
On the Rate of Convergence of Empirical Measures in ∞-transportation DistanceCanadian Journal of Mathematics, 67
N. Trillos, D. Slepčev (2015)
A variational approach to the consistency of spectral clusteringArXiv, abs/1508.01928
Yang Wang, M. Cheema, Xuemin Lin, Qing Zhang (2013)
Multi-Manifold Ranking: Using Multiple Features for Better Image Retrieval
Dengyong Zhou, Bernhard Schölkopf (2005)
Lecture Notes in Computer Science
Dengyong Zhou, Jiayuan Huang, B. Scholkopf (2005)
Learning from labeled and unlabeled data on a directed graphProceedings of the 22nd international conference on Machine learning
J. Sundnes, G. Lines, X. Cai, B. Nielsen, K. Mardal, A. Tveito (2006)
Solving Linear Systems
C Villani (2009)
Optimal transport, Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences]
A. Alaoui (2016)
Asymptotic behavior of \(\ell_p\)-based Laplacian regularization in semi-supervised learning
Rasmus Kyng, Anup Rao, Sushant Sachdeva, D. Spielman (2015)
Algorithms for Lipschitz Learning on Graphs
Matthew Dunlop, D. Slepčev, A. Stuart, Matthew Thorpe (2018)
Large Data and Zero Noise Limits of Graph-Based Semi-Supervised Learning AlgorithmsArXiv, abs/1805.09450
M. Ajtai, J. Komlos, G. Tusnády (1984)
On optimal matchingsCombinatorica, 4
Xueyuan Zhou, M. Belkin (2011)
Semi-supervised Learning by Higher Order Regularization
PROPERLY-WEIGHTED GRAPH LAPLACIAN
W. Rudin (1968)
Real and complex analysis
Dengyong Zhou, B. Scholkopf (2005)
Regularization on Discrete Spaces
F Santambrogio (2015)
Optimal Transport for Applied Mathematicians, Progress in Nonlinear Differential Equations and their Applications Calculus of variations, PDEs, and modeling
M Talagrand (2014)
Upper and Lower Bounds of Stochastic Processes. Modern Surveys in Mathematics
G. Maso (1993)
An Introduction to [gamma]-convergence
F. Leighton, P. Shor (1989)
Tight bounds for minimax grid matching with applications to the average case analysis of algorithmsCombinatorica, 9
Nick Bridle, Xiaojin Zhu (2013)
p-voltages: Laplacian Regularization for Semi-Supervised Learning on High-Dimensional Data
A. Bertozzi, Xiyang Luo, A. Stuart, K. Zygalakis (2017)
Uncertainty Quantification in Graph-Based Classification of High Dimensional DataSIAM/ASA J. Uncertain. Quantification, 6
C. McBride, C. Snow, N. Kucirkova, V. Grøver (2017)
Old and new
M. Talagrand (2014)
Upper and Lower Bounds for Stochastic Processes: Modern Methods and Classical Problems
N. Trillos, Dejan Slepvcev (2014)
On the rate of convergence of empirical measures in $\infty$-transportation distancearXiv: Probability
U. Luxburg, O. Bousquet (2004)
Distance-Based Classification with Lipschitz Functions
G. Leoni (2017)
A First Course in Sobolev Spaces: Second Edition
Jia Deng, Wei Dong, R. Socher, Li-Jia Li, K. Li, Li Fei-Fei (2009)
ImageNet: A large-scale hierarchical image database2009 IEEE Conference on Computer Vision and Pattern Recognition
Xueyuan Zhou, M. Belkin, N. Srebro (2011)
An iterated graph laplacian approach for ranking on manifolds
B. Nadler, N. Srebro, Xueyuan Zhou (2009)
Semi-supervised learning with the graph Laplacian: the limit of infinite unlabelled data
Yang Wang, Muhammad Aamir Cheema, Xuemin Lin, Qing Zhang (2013)
Advances in Knowledge Discovery and Data Mining
M. Belkin, P. Niyogi (2002)
Using Manifold Stucture for Partially Labeled Classification
N García Trillos, D Slepčev (2015)
On the rate of convergence of empirical measures in $$\infty $$ ∞ -transportation distanceCan. J. Math., 67
D. Slepčev, Matthew Thorpe (2017)
Analysis of $p$-Laplacian Regularization in Semi-Supervised LearningSIAM J. Math. Anal., 51
J. Ruge, K. Stüben (1987)
4. Algebraic Multigrid
J. Calder, Charles Smart (2018)
The limit shape of convex hull peelingArXiv, abs/1805.08278
A. Goldberg, Xiaojin Zhu, Aarti Singh, Zhiting Xu, Robert Nowak (2009)
Multi-Manifold Semi-Supervised Learning
Dengyong Zhou, J. Weston, A. Gretton, O. Bousquet, B. Scholkopf (2003)
Ranking on Data Manifolds
P. Shor, J. Yukich (1991)
Minimax Grid Matching and Empirical MeasuresAnnals of Probability, 19
G. Maso (1993)
An Introduction to-convergence
Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations
The performance of traditional graph Laplacian methods for semi-supervised learning degrades substantially as the ratio of labeled to unlabeled data decreases, due to a degeneracy in the graph Laplacian. Several approaches have been proposed recently to address this, however we show that some of them remain ill-posed in the large- data limit. In this paper, we show a way to correctly set the weights in Laplacian regularization so that the estimator remains well posed and stable in the large-sample limit. We prove that our semi-supervised learning algorithm converges, in the infinite sample size limit, to the smooth solution of a continuum variational problem that attains the labeled values continuously. Our method is fast and easy to implement. Keywords Semi-supervised learning · Label propagation · Asymptotic consistency · PDEs on graphs · Gamma-convergence Mathematics Subject Classification 49J55 · 35J20 · 35B65 · 62G20 · 65N12 1 Introduction For many applications of machine learning, such as medical image classification and speech recognition, labeling data requires human input and is expensive [13], while unlabeled data is relatively cheap. Semi-supervised learning aims to exploit this dichotomy by utilizing the geometric or topological properties of the unlabeled data, in conjunction with the labeled data,
Applied Mathematics and Optimization – Springer Journals
Published: Dec 7, 2019
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.