There's a hole in my data space: Piecewise predictors for heterogeneous learning problems

Journal of Machine Learning Research

Volumn 22, Issue , 2012, Pages 291-298

  Dekel, Ofer ^a   Shamir, Ohad ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ARTIFICIAL INTELLIGENCE; CONVEX OPTIMIZATION; ERRORS; ITERATIVE METHODS;

CLASSIFICATION ALGORITHM; CONVEX OPTIMIZATION PROBLEMS; DATA PREPROCESSING; FEATURE ENGINEERINGS; LEARNING PROBLEM; SAMPLE COMPLEXITY; STATISTICAL LEARNING; STOCHASTIC OPTIMIZATION ALGORITHM;

OPTIMIZATION;

EID: 84954231221     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (15)

1. A. Azran and R. Meir. Data dependent risk bounds for hierarchical mixture of experts classifiers. In COLT, 2004.
2. P. Bartlett and S. Mendelson. Rademacher and gaussian complexities: Risk bounds and structural results. JMLR, 3:463-482, 2002.
3. L. Bobrowski. Piecewise-linear classifiers, formal neurons and separability of the learning sets. In ICPR, 1996.
4. O. Bousquet Boucheron, S. and G. Lugosi. Theory of classification: A survey of some recent advances. ESAIM: Probability and Statistics, 9:323-375, 2005.
5. J. Dai, S. Yan, X. Tang, and J. Kwok. Locally adaptive classification piloted by uncertainty. In ICML, 2006.
6. P. Hartono. Ensemble of linear experts as an in-terpretable piecewise-linear classifier. ICIC Express Letters, 2(3), 2008.
7. A. Kostin. A simple and fast multi-class piece-wise linear pattern classifier. Pattern Recognition, 39:1949-1962, 2006.
8. R. Meir, R. El-Yaniv, and S. Ben-David. Localized boosting. In COLT, 2000.
9. A. Nedic and A. Ozdaglar. Subgradient methods for saddle point problems. J. of Optimization Theory and Applications, 142(1):205-228, 2009.
10. Yu. Nesterov. Primal-dual subgradient methods for convex problems. Mathematical Programming, 120(1):221-259, August 2009.
11. S. Shalev-Shwartz, Y. Singer, and N. Srebro. Pe-gasos: Primal Estimated sub-GrAdient SOlver for SVM. In ICML, 2007.
12. O. Shamir. A variant of azuma's inequality for martingales with subgaussian tails. ArXiv Technical Report, 2011.
13. M. Toussaint and S. Vijayakumar. Learning discontinuities with products-of-sigmoids for switching between local models. In ICML, 2005.
14. L. Xiao. Dual averaging methods for regularized stochastic learning and online optimization. Journal of Machine Learning Research, 11:2543-2596, 2010.
15. L. Yujian, L. Bo, Y. Xinwu, F. Yaozong, and L. Houjun. Multiconlitron: A general piecewise linear classifier. IEEE Trans. Neural Networks, 22(2):276-289, 2011.