Access the full text.
Sign up today, get DeepDyve free for 14 days.
P. Niyogi, F. Girosi, T. Poggio (1998)
Incorporating prior information in machine learning by creating virtual examplesProc. IEEE, 86
B. Haasdonk, H. Burkhardt (2007)
Invariant kernel functions for pattern analysis and machine learningMachine Learning, 68
H. Schulz-Mirbach (1994)
Constructing invariant features by averaging techniquesProceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5), 2
U. Luxburg, B. Scholkopf (2008)
Statistical Learning Theory: Models, Concepts, and Results
M. Eaton (1989)
Group invariance applications in statistics
F Lauer, G Bloch (2008)
Incorporating prior knowledge in support vector regressionMach Learn, 70
Machine Learning manuscript No. (will be inserted by the editor) Incorporating Prior Knowledge in Support Vector Regression
D. Wolpert, W. Macready (1997)
No free lunch theorems for optimizationIEEE Trans. Evol. Comput., 1
C. Teo, A. Globerson, S. Roweis, Alex Smola (2007)
Convex Learning with Invariances
T. Graepel, R. Herbrich (2003)
Invariant Pattern Recognition by Semi-Definite Programming Machines
M. Kumar, P. Torr, Andrew Zisserman (2007)
An Invariant Large Margin Nearest Neighbour Classifier2007 IEEE 11th International Conference on Computer Vision
PY Simard, YL Cun, JS Denker (1993)
Advances in neural information processing systems 5
R. Kondor, T. Jebara (2003)
A Kernel Between Sets of Vectors
Yuhai Wu (2021)
Statistical Learning TheoryTechnometrics, 41
D. DeCoste, B. Scholkopf (2002)
Training Invariant Support Vector MachinesMachine Learning, 46
(2003)
Fawcett T, Mishra N (eds) Proceedings of the 20th International Conference on Machine Learning (ICML’03), pp 361–368
Amir Atiya (2005)
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and BeyondIEEE Transactions on Neural Networks, 16
J. Wood (1996)
Invariant pattern recognition: A reviewPattern Recognit., 29
Vladimir Vapni (1995)
The Nature of Statistical Learning Theory
C. Bhattacharyya, Pannagadatta Shivaswamy, Alex Smola (2004)
A Second Order Cone programming Formulation for Classifying Missing Data
M. Reisert, H. Burkhardt (2007)
Learning Equivariant Functions with Matrix Valued KernelsJ. Mach. Learn. Res., 8
A. Vedaldi, Matthew Blaschko, Andrew Zisserman (2011)
Learning equivariant structured output SVM regressors2011 International Conference on Computer Vision
Lei Wang, Yan Gao, K. Chan, P. Xue, W. Yau (2005)
Retrieval with knowledge-driven kernel design: an approach to improving SVM-based CBIR with relevance feedbackTenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2
Pannagadatta Shivaswamy, T. Jebara (2006)
Permutation invariant SVMsProceedings of the 23rd international conference on Machine learning
Fabien Lauer, G. Bloch (2008)
Incorporating prior knowledge in support vector machines for classification: A reviewNeurocomputing, 71
P. Simard, Yann LeCun, J. Denker (1992)
Efficient Pattern Recognition Using a New Transformation Distance
(2008)
Group theoretical methods in machine learning
T. Jebara (2003)
Convex Invariance Learning
B. Scholkopf, C. Burges, V. Vapnik (1996)
Incorporating Invariances in Support Vector Learning Machines
P. Simard, Yann LeCun, J. Denker, B. Victorri (1996)
Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation
Statistical learning theory (SLT) provides the theoretical basis for many machine learning algorithms (e.g. SVMs and kernel methods). Invariance, as one type of popular prior knowledge in pattern analysis, has been widely incorporated into various statistical learning algorithms to improve learning performance. Though successful in some applications, existing invariance learning algorithms are task-specific, and lack a solid theoretical basis including consistency. In this paper, we first propose the problem of statistical learning with group invariance (or group invariance learning in short) to provide a unifying framework for existing invariance learning algorithms in pattern analysis by exploiting group invariance. We then introduce the group invariance empirical risk minimization (GIERM) method to solve the group invariance learning problem, which incorporates the group action on the original data into empirical risk minimization (ERM). Finally, we investigate the consistency of the GIERM method in detail. Our theoretical results include three theorems, covering the necessary and sufficient conditions of consistency, uniform two-sided convergence and uniform one-sided convergence for the group invariance learning process based on the GIERM method.
International Journal of Machine Learning and Cybernetics – Springer Journals
Published: Jun 5, 2018
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.