메뉴 건너뛰기




Volumn 78, Issue 3, 2010, Pages 287-304

Random classification noise defeats all convex potential boosters

Author keywords

Boosting; Convex loss; Learning theory; Misclassification noise; Noise tolerant learning; Potential boosting

Indexed keywords

ADAPTIVE BOOSTING; ALGORITHMS; CONVEX PROGRAMMING;

EID: 83555170269     PISSN: 08856125     EISSN: 15730565     Source Type: Journal    
DOI: 10.1007/s10994-009-5165-z     Document Type: Article
Times cited : (190)

References (26)
  • 3
    • 80555137399 scopus 로고    scopus 로고
    • Department of Statistics. Berkeley: University of California
    • Breiman, L. (1997). Arcing the edge (Technical report 486). Department of Statistics. Berkeley: University of California.
    • (1997) Arcing the Edge (Technical Report 486)
    • Breiman, L.1
  • 4
    • 14644395930 scopus 로고    scopus 로고
    • Some infinity theory for predictor ensembles
    • Breiman, L. (2004). Some infinity theory for predictor ensembles. Annals of Statistics, 32(1), 1-11.
    • (2004) Annals of Statistics , vol.32 , Issue.1 , pp. 1-11
    • Breiman, L.1
  • 5
    • 0034250160 scopus 로고    scopus 로고
    • An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization
    • Dietterich, T.G. (2000). An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Machine Learning, 40(2), 139-158.
    • (2000) Machine Learning , vol.40 , Issue.2 , pp. 139-158
    • Dietterich, T.G.1
  • 8
    • 0037031029 scopus 로고    scopus 로고
    • A geometric approach to leveraging weak learners
    • DOI 10.1016/S0304-3975(01)00083-4, PII S0304397501000834
    • Duffy, N., & Helmbold, D. (2002). A geometric approach to leveraging weak learners. Theoretical Computer Science, 284, 67-108. (Pubitemid 34661530)
    • (2002) Theoretical Computer Science , vol.284 , Issue.1 , pp. 67-108
    • Duffy, N.1    Helmbold, D.2
  • 9
    • 58149321460 scopus 로고
    • Boosting a weak learning algorithm by majority
    • Freund, Y. (1995). Boosting a weak learning algorithm by majority. Information and Computation, 121(2), 256-285.
    • (1995) Information and Computation , vol.121 , Issue.2 , pp. 256-285
    • Freund, Y.1
  • 10
    • 0035371148 scopus 로고    scopus 로고
    • An adaptive version of the boost-by-majority algorithm
    • Freund, Y. (2001). An adaptive version of the boost-by-majority algorithm. Machine Learning, 43(3), 293-318.
    • (2001) Machine Learning , vol.43 , Issue.3 , pp. 293-318
    • Freund, Y.1
  • 12
    • 0031211090 scopus 로고    scopus 로고
    • A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
    • Freund, Y. & Schapire, R. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119-139. (Pubitemid 127433398)
    • (1997) Journal of Computer and System Sciences , vol.55 , Issue.1 , pp. 119-139
    • Freund, Y.1    Schapire, R.E.2
  • 13
    • 0034164230 scopus 로고    scopus 로고
    • Additive logistic regression: A statistical view of boosting
    • Friedman, J., Hastie, T., & Tibshirani, R. (1998). Additive logistic regression: a statistical view of boosting. Annals of Statistics, 28(2), 337-407. (Pubitemid 33227445)
    • (2000) Annals of Statistics , vol.28 , Issue.2 SPI. , pp. 337-407
    • Friedman, J.1    Hastie, T.2    Tibshirani, R.3
  • 14
    • 24644494284 scopus 로고    scopus 로고
    • Boosting in the presence of noise
    • DOI 10.1016/j.jcss.2004.10.015, PII S0022000004001382
    • Kalai, A., & Servedio, R. (2005). Boosting in the presence of noise. Journal of Computer & System Sciences, 71(3), 266-290. (Pubitemid 41278181)
    • (2005) Journal of Computer and System Sciences , vol.71 , Issue.3 , pp. 266-290
    • Kalai, A.T.1    Servedio, R.A.2
  • 17
    • 9444269961 scopus 로고    scopus 로고
    • On the Bayes-risk consistency of regularized boosting methods
    • DOI 10.1214/aos/1079120129
    • Lugosi, G., & Vayatis, N. (2004). On the bayes-risk consistency of regularized boosting methods. Annals of Statistics, 32(1), 30-55. (Pubitemid 41449304)
    • (2004) Annals of Statistics , vol.32 , Issue.1 , pp. 30-55
    • Lugosi, G.1    Vayatis, N.2
  • 22
    • 0342502195 scopus 로고    scopus 로고
    • Soft margins for AdaBoost
    • DOI 10.1023/A:1007618119488
    • Ratsch, G., Onoda, T., & Müller, K.-R. (2001). Soft margins for AdaBoost. Machine Learning, 42(3), 287-320. (Pubitemid 32188795)
    • (2001) Machine Learning , vol.42 , Issue.3 , pp. 287-320
    • Ratsch, G.1    Onoda, T.2    Muller, K.-R.3
  • 23
    • 0033281701 scopus 로고    scopus 로고
    • Improved boosting algorithms using confidence-rated predictions
    • DOI 10.1023/A:1007614523901
    • Schapire, R., & Singer, Y. (1999). Improved boosting algorithms using confidence-rated predictions. Machine Learning, 37, 297-336. (Pubitemid 32210620)
    • (1999) Machine Learning , vol.37 , Issue.3 , pp. 297-336
    • Schapire, R.E.1    Singer, Y.2
  • 24
    • 2542488394 scopus 로고    scopus 로고
    • Smooth boosting and learning with malicious noise
    • Servedio, R. (2003). Smooth boosting and learning with malicious noise. Journal of Machine Learning Research, 4, 633-648.
    • (2003) Journal of Machine Learning Research , vol.4 , pp. 633-648
    • Servedio, R.1
  • 25
    • 4644257995 scopus 로고    scopus 로고
    • Statistical behavior and consistency of classification methods based on convex risk minimization
    • Zhang, T. (2004). Statistical behavior and consistency of classification methods based on convex risk minimization. Annals of Statistics, 32(1), 56-85.
    • (2004) Annals of Statistics , vol.32 , Issue.1 , pp. 56-85
    • Zhang, T.1
  • 26
    • 26444493144 scopus 로고    scopus 로고
    • Boosting with early stopping: Convergence and consistency
    • DOI 10.1214/009053605000000255
    • Zhang, T., & Yu, B. (2005). Boosting with early stopping: Convergence and consistency. Annals of Statistics, 33(4), 1538-1579. (Pubitemid 41423980)
    • (2005) Annals of Statistics , vol.33 , Issue.4 , pp. 1538-1579
    • Zhang, T.1    Yu, B.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.