메뉴 건너뛰기




Volumn , Issue , 2010, Pages 218-230

Online learning of noisy data with kernels

Author keywords

[No Author keywords available]

Indexed keywords

GAUSSIAN KERNELS; GRADIENT DESCENT; HIGH PROBABILITY; MULTIPLE QUERIES; NOISE DISTRIBUTION; NONLINEAR FUNCTIONS; ONLINE LEARNING; UNBIASED ESTIMATOR;

EID: 84870176618     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (11)

References (18)
  • 1
    • 84898063697 scopus 로고    scopus 로고
    • Competing in the dark: An efficient algorithm for bandit linear optimization
    • J. Abernethy, E. Hazan, and A. Rakhlin. Competing in the dark: An efficient algorithm for bandit linear optimization. In COLT, pages 263-274, 2008.
    • (2008) COLT , pp. 263-274
    • Abernethy, J.1    Hazan, E.2    Rakhlin, A.3
  • 2
    • 83255166878 scopus 로고
    • Existence of unbiased estimators in sequential binomial experiments
    • S. Bhandari and A. Bose. Existence of unbiased estimators in sequential binomial experiments. Sankhya: The Indian Journal of Statistics, 52(1):127-130, 1990.
    • (1990) Sankhya: The Indian Journal of Statistics , vol.52 , Issue.1 , pp. 127-130
    • Bhandari, S.1    Bose, A.2
  • 3
    • 0347596605 scopus 로고    scopus 로고
    • Uniform-distribution attribute noise learnability
    • N. Bshouty, J. Jackson, and C. Tamon. Uniform-distribution attribute noise learnability. Information and Computation, 187(2):277-290, 2003.
    • (2003) Information and Computation , vol.187 , Issue.2 , pp. 277-290
    • Bshouty, N.1    Jackson, J.2    Tamon, C.3
  • 8
    • 20744454447 scopus 로고    scopus 로고
    • Online convex optimization in the bandit setting: Gradient descent without a gradient
    • A. Flaxman, A. Tauman Kalai, and H. McMahan. Online convex optimization in the bandit setting: gradient descent without a gradient. In Proceedings of SODA, pages 385-394, 2005.
    • (2005) Proceedings of SODA , pp. 385-394
    • Flaxman, A.1    Tauman Kalai, A.2    McMahan, H.3
  • 9
    • 0013411860 scopus 로고
    • Can pac learning algorithms tolerate random attribute noise?
    • S. Goldman and R. Sloan. Can pac learning algorithms tolerate random attribute noise? Al-gorithmica, 14(1):70-84, 1995.
    • (1995) Al-gorithmica , vol.14 , Issue.1 , pp. 70-84
    • Goldman, S.1    Sloan, R.2
  • 10
    • 0027640858 scopus 로고
    • Learning in the presence of Malicious errors
    • M. Kearns and M. Li. Learning in the presence of malicious errors. SIAM Journal on Computing, 22(4):807-837, 1993.
    • (1993) SIAM Journal on Computing , vol.22 , Issue.4 , pp. 807-837
    • Kearns, M.1    Li, M.2
  • 11
    • 0000511449 scopus 로고
    • Redundant noisy attributes, attribute errors, and linear threshold learning using winnow
    • N. Littlestone. Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow. In Proceedings of COLT, pages 147-156, 1991.
    • (1991) Proceedings of COLT , pp. 147-156
    • Littlestone, N.1
  • 12
    • 84898030282 scopus 로고    scopus 로고
    • A study of the effect of different types of noise on the precision of supervised learning techniques
    • D. Nettleton, A. Orriols-Puig, and A. Fornells. A study of the effect of different types of noise on the precision of supervised learning techniques. Artificial Intelligence Review, 2010.
    • (2010) Artificial Intelligence Review
    • Nettleton, D.1    Orriols-Puig, A.2    Fornells, A.3
  • 14
    • 0041877169 scopus 로고    scopus 로고
    • Estimation of entropy and mutual information
    • L. Paninski. Estimation of entropy and mutual information. Neural Computation, 15(6):1191-1253, 2003.
    • (2003) Neural Computation , vol.15 , Issue.6 , pp. 1191-1253
    • Paninski, L.1
  • 18
    • 1942484421 scopus 로고    scopus 로고
    • Online convex programming and generalized infinitesimal gradient ascent
    • M. Zinkevich. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of ICML, pages 928-936, 2003.
    • (2003) Proceedings of ICML , pp. 928-936
    • Zinkevich, M.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.