메뉴 건너뛰기




Volumn 90, Issue 3, 2013, Pages 431-460

Computational complexity of kernel-based density-ratio estimation: A condition number analysis

Author keywords

Condition number; Density ratio; Kernel; Smoothed analysis

Indexed keywords

COMPUTATIONAL PROPERTIES; CONDITION NUMBERS; CONVERGENCE RATES; DENSITY-RATIO; DENSITY-RATIO ESTIMATIONS; HESSIAN MATRICES; KERNEL; LEAST SQUARE; LEAST SQUARES METHODS; LEAST-SQUARES ESTIMATOR; LOSS FUNCTIONS; M-ESTIMATORS; NUMERICAL EXPERIMENTS; SMOOTHED ANALYSIS;

EID: 84874701688     PISSN: 08856125     EISSN: 15730565     Source Type: Journal    
DOI: 10.1007/s10994-012-5323-6     Document Type: Article
Times cited : (14)

References (92)
  • 4
    • 65849142997 scopus 로고    scopus 로고
    • Robin-robin preconditioned Krylov methods for fluid-structure interaction problems
    • 2532370 1228.76079 10.1016/j.cma.2009.04.004
    • Badia, S., Nobile, F., & Vergara, C. (2009). Robin-robin preconditioned Krylov methods for fluid-structure interaction problems. Computer Methods in Applied Mechanics and Engineering, 198, 2768-2784.
    • (2009) Computer Methods in Applied Mechanics and Engineering , vol.198 , pp. 2768-2784
    • Badia, S.1    Nobile, F.2    Vergara, C.3
  • 6
    • 33846869297 scopus 로고    scopus 로고
    • Estimates on the distribution of the condition number of singular matrices
    • 2283343 10.1007/s10208-005-0176-2
    • Beltran, C., & Pardo, L. M. (2006). Estimates on the distribution of the condition number of singular matrices. Foundations of Computational Mathematics, 7, 87-134.
    • (2006) Foundations of Computational Mathematics , vol.7 , pp. 87-134
    • Beltran, C.1    Pardo, L.M.2
  • 7
    • 80051879605 scopus 로고    scopus 로고
    • A preconditioning technique for a class of PDE-constrained optimization problems
    • 2827084 05988495 10.1007/s10444-011-9173-8
    • Benzi, M., Haber, E., & Taralli, L. (2011). A preconditioning technique for a class of PDE-constrained optimization problems. Advances in Computational Mathematics, 35, 149-173.
    • (2011) Advances in Computational Mathematics , vol.35 , pp. 149-173
    • Benzi, M.1    Haber, E.2    Taralli, L.3
  • 11
    • 0022709623 scopus 로고
    • Evaluating rational functions: Infinite precision is finite cost and tractable on average
    • 837590 0622.68038 10.1137/0215026
    • Blum, L., & Shub, M. (1986). Evaluating rational functions: infinite precision is finite cost and tractable on average. SIAM Journal on Computing, 15, 384-398.
    • (1986) SIAM Journal on Computing , vol.15 , pp. 384-398
    • Blum, L.1    Shub, M.2
  • 13
    • 33751051746 scopus 로고    scopus 로고
    • The complexity of semilinear problems in succinct representation
    • 2268403 1113.68057 10.1007/s00037-006-0213-6
    • Bürgisser, P., Cucker, F., & de Naurois, P. (2006a). The complexity of semilinear problems in succinct representation. Computational Complexity, 15, 197-235.
    • (2006) Computational Complexity , vol.15 , pp. 197-235
    • Bürgisser, P.1    Cucker, F.2    De Naurois, P.3
  • 16
    • 77953646724 scopus 로고    scopus 로고
    • Coverage processes on spheres and condition numbers for linear programming
    • 2642886 1205.60027 10.1214/09-AOP489
    • Bürgisser, P., Cucker, F., & Lotz, M. (2010). Coverage processes on spheres and condition numbers for linear programming. Annals of Probability, 38, 570-604.
    • (2010) Annals of Probability , vol.38 , pp. 570-604
    • Bürgisser, P.1    Cucker, F.2    Lotz, M.3
  • 18
    • 34247849152 scopus 로고    scopus 로고
    • Training a support vector machine in the primal
    • 2309267 1123.68101 10.1162/neco.2007.19.5.1155
    • Chapelle, O. (2007). Training a support vector machine in the primal. Neural Computation, 19, 1155-1178.
    • (2007) Neural Computation , vol.19 , pp. 1155-1178
    • Chapelle, O.1
  • 19
    • 0036262238 scopus 로고    scopus 로고
    • Probabilistic analysis of condition numbers for linear programming
    • 1910854 1041.90028 10.1023/A:1015460004163
    • Cheung, D., & Cucker, F. (2002). Probabilistic analysis of condition numbers for linear programming. Journal of Optimization Theory and Applications, 114, 55-67.
    • (2002) Journal of Optimization Theory and Applications , vol.114 , pp. 55-67
    • Cheung, D.1    Cucker, F.2
  • 20
    • 0000489740 scopus 로고
    • Information-type measures of difference of probability distributions and indirect observation
    • Csiszár, I. (1967). Information-type measures of difference of probability distributions and indirect observation. Studia Scientiarum Mathematicarum Hungarica, 2, 229-318.
    • (1967) Studia Scientiarum Mathematicarum Hungarica , vol.2 , pp. 229-318
    • Csiszár, I.1
  • 21
    • 0142055280 scopus 로고    scopus 로고
    • On the expected condition number of linear programming problems
    • 1981163
    • Cucker, F., & Wschebor, M. (2002). On the expected condition number of linear programming problems. Numerische Mathematik, 94, 94-419.
    • (2002) Numerische Mathematik , vol.94 , pp. 94-419
    • Cucker, F.1    Wschebor, M.2
  • 22
    • 84966237760 scopus 로고
    • The probability that a numerical analysis problem is difficult
    • 929546 0657.65066 10.1090/S0025-5718-1988-0929546-7
    • Demmel, J. (1988). The probability that a numerical analysis problem is difficult. Mathematics of Computation, 50, 449-480.
    • (1988) Mathematics of Computation , vol.50 , pp. 449-480
    • Demmel, J.1
  • 24
    • 0000802374 scopus 로고
    • The approximation of one matrix by another of lower rank
    • JFM 62.1075.02 10.1007/BF02288367
    • Eckart, C., & Young, G. (1936). The approximation of one matrix by another of lower rank. Psychometrika, 1, 211-218.
    • (1936) Psychometrika , vol.1 , pp. 211-218
    • Eckart, C.1    Young, G.2
  • 25
    • 0000324960 scopus 로고
    • Eigenvalues and condition numbers of random matrices
    • 964668 0678.15019 10.1137/0609045
    • Edelman, A. (1988). Eigenvalues and condition numbers of random matrices. SIAM Journal on Matrix Analysis and Applications, 9, 543-560.
    • (1988) SIAM Journal on Matrix Analysis and Applications , vol.9 , pp. 543-560
    • Edelman, A.1
  • 26
    • 84968515219 scopus 로고
    • On the distribution of a scaled condition number
    • 1106966 0745.15012 10.1090/S0025-5718-1992-1106966-2
    • Edelman, A. (1992). On the distribution of a scaled condition number. Mathematics of Computation, 58, 185-190.
    • (1992) Mathematics of Computation , vol.58 , pp. 185-190
    • Edelman, A.1
  • 28
    • 70349847999 scopus 로고    scopus 로고
    • Covariate shift by kernel mean matching
    • J. Quiñonero-Candela M. Sugiyama A. Schwaighofer N. Lawrence (eds) MIT Press Cambridge
    • Gretton, A., Smola, A., Huang, J., Schmittfull, M., Borgwardt, K., & Schölkopf, B. (2009). Covariate shift by kernel mean matching. In J. Quiñonero-Candela, M. Sugiyama, A. Schwaighofer, & N. Lawrence (Eds.), Dataset shift in machine learning (pp. 131-160). Cambridge: MIT Press.
    • (2009) Dataset Shift in Machine Learning , pp. 131-160
    • Gretton, A.1    Smola, A.2    Huang, J.3    Schmittfull, M.4    Borgwardt, K.5    Schölkopf, B.6
  • 29
    • 33745276908 scopus 로고    scopus 로고
    • A survey of the nonlinear conjugate gradient methods
    • 2548208 1117.90048
    • Hager, W. W., & Zhang, H. (2006). A survey of the nonlinear conjugate gradient methods. Pacific Journal of Optimization, 2, 35-58.
    • (2006) Pacific Journal of Optimization , vol.2 , pp. 35-58
    • Hager, W.W.1    Zhang, H.2
  • 32
    • 0004151494 scopus 로고
    • Cambridge University Press Cambridge 0576.15001
    • Horn, R., & Johnson, C. (1985). Matrix analysis. Cambridge: Cambridge University Press.
    • (1985) Matrix Analysis
    • Horn, R.1    Johnson, C.2
  • 33
    • 68949141755 scopus 로고    scopus 로고
    • A least-squares approach to direct importance estimation
    • 2534866 1235.62039
    • Kanamori, T., Hido, S., & Sugiyama, M. (2009). A least-squares approach to direct importance estimation. Journal of Machine Learning Research, 10, 1391-1445.
    • (2009) Journal of Machine Learning Research , vol.10 , pp. 1391-1445
    • Kanamori, T.1    Hido, S.2    Sugiyama, M.3
  • 34
    • 84867133788 scopus 로고    scopus 로고
    • Statistical analysis of kernel-based least-squares density-ratio estimation
    • 2897527 1246.68182 10.1007/s10994-011-5266-3
    • Kanamori, T., Suzuki, T., & Sugiyama, M. (2012). Statistical analysis of kernel-based least-squares density-ratio estimation. Machine Learning, 86, 335-367.
    • (2012) Machine Learning , vol.86 , pp. 335-367
    • Kanamori, T.1    Suzuki, T.2    Sugiyama, M.3
  • 36
    • 84858312965 scopus 로고    scopus 로고
    • Sequential change-point detection based on direct density-ratio estimation
    • 2910022 10.1002/sam.10124
    • Kawahara, Y., & Sugiyama, M. (2011). Sequential change-point detection based on direct density-ratio estimation. Statistical Analysis and Data Mining, 5, 114-127.
    • (2011) Statistical Analysis and Data Mining , vol.5 , pp. 114-127
    • Kawahara, Y.1    Sugiyama, M.2
  • 39
    • 0009712181 scopus 로고
    • Complexity theory of numerical linear algebra
    • 956504 0645.65019 10.1016/0377-0427(88)90402-5
    • Kostlan, E. (1988). Complexity theory of numerical linear algebra. Journal of Computational and Applied Mathematics, 22, 219-230.
    • (1988) Journal of Computational and Applied Mathematics , vol.22 , pp. 219-230
    • Kostlan, E.1
  • 41
    • 75649121507 scopus 로고    scopus 로고
    • Worst-case and smoothed analysis of k-means clustering with Bregman divergences
    • Manthey, B., & Röglin, H. (2009). Worst-case and smoothed analysis of k-means clustering with Bregman divergences. In ISAAC (pp. 1024-1033).
    • (2009) ISAAC , pp. 1024-1033
    • Manthey, B.1    Röglin, H.2
  • 45
    • 77958588617 scopus 로고    scopus 로고
    • Estimating divergence functionals and the likelihood ratio by convex risk minimization
    • 2808937 10.1109/TIT.2010.2068870
    • Nguyen, X., Wainwright, M. J., & Jordan, M. I. (2010). Estimating divergence functionals and the likelihood ratio by convex risk minimization. IEEE Transactions on Information Theory, 56, 5847-5861.
    • (2010) IEEE Transactions on Information Theory , vol.56 , pp. 5847-5861
    • Nguyen, X.1    Wainwright, M.J.2    Jordan, M.I.3
  • 48
    • 70149113077 scopus 로고    scopus 로고
    • R Development Core Team R Foundation for Statistical Computing Vienna 3-900051-07-0
    • R Development Core Team (2009). R: a language and environment for statistical computing. Vienna: R Foundation for Statistical Computing. ISBN 3-900051-07-0.
    • (2009) R: A Language and Environment for Statistical Computing
  • 50
    • 0342502195 scopus 로고    scopus 로고
    • Soft margins for adaboost
    • 0969.68128 10.1023/A:1007618119488
    • Rätsch, G., Onoda, T., & Müller, K.-R. (2001). Soft margins for adaboost. Machine Learning, 42, 287-320.
    • (2001) Machine Learning , vol.42 , pp. 287-320
    • Rätsch, G.1    Onoda, T.2    Müller, K.-R.3
  • 51
    • 0023292476 scopus 로고
    • On the efficiency of newton's method in approximating all zeros of a system of complex polynomials
    • 882846 0618.65038 10.1287/moor.12.1.121
    • Renegar, J. (1987). On the efficiency of newton's method in approximating all zeros of a system of complex polynomials. Mathematics of Operations Research, 12, 121-148.
    • (1987) Mathematics of Operations Research , vol.12 , pp. 121-148
    • Renegar, J.1
  • 52
    • 0000208672 scopus 로고
    • Incorporating condition measures into the complexity theory of linear programming
    • Renegar, J. (1995). Incorporating condition measures into the complexity theory of linear programming. SIAM Journal on Optimization, 5.
    • (1995) SIAM Journal on Optimization , pp. 5
    • Renegar, J.1
  • 53
    • 0004267646 scopus 로고
    • Princeton University Press Princeton 0193.18401
    • Rockafellar, R. T. (1970). Convex analysis. Princeton: Princeton University Press.
    • (1970) Convex Analysis
    • Rockafellar, R.T.1
  • 54
    • 33947146755 scopus 로고    scopus 로고
    • Smoothed analysis of integer programming
    • 2306129 1111.90077 10.1007/s10107-006-0055-7
    • Röglin, H., & Vöcking, B. (2007). Smoothed analysis of integer programming. Mathematical Programming, 110, 21-56.
    • (2007) Mathematical Programming , vol.110 , pp. 21-56
    • Röglin, H.1    Vöcking, B.2
  • 55
    • 34247360062 scopus 로고    scopus 로고
    • Smoothed analysis of the condition numbers and growth factors of matrices
    • 2255338 1179.65033 10.1137/S0895479803436202
    • Sankar, A., Spielman, D. A., & Teng, S.-H. (2006). Smoothed analysis of the condition numbers and growth factors of matrices. SIAM Journal on Matrix Analysis and Applications, 28, 446-476.
    • (2006) SIAM Journal on Matrix Analysis and Applications , vol.28 , pp. 446-476
    • Sankar, A.1    Spielman, D.A.2    Teng, S.-H.3
  • 56
    • 85162564991 scopus 로고    scopus 로고
    • Convergence rates of inexact proximal-gradient methods for convex optimization
    • J. Shawe-Taylor R. Zemel Bartlett F. Pereira K. Weinberger (eds) 24
    • Schmidt, M., Le Roux, N., & Bach, F. (2011). Convergence rates of inexact proximal-gradient methods for convex optimization. In J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, & K. Weinberger (Eds.), Advances in neural information processing systems (Vol. 24, pp. 1458-1466).
    • (2011) Advances in Neural Information Processing Systems , pp. 1458-1466
    • Schmidt, M.1    Le Roux, N.2    Bach, F.3
  • 58
    • 0037527188 scopus 로고    scopus 로고
    • Improving predictive inference under covariate shift by weighting the log-likelihood function
    • 1795598 0958.62011 10.1016/S0378-3758(00)00115-4
    • Shimodaira, H. (2000). Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90, 227-244.
    • (2000) Journal of Statistical Planning and Inference , vol.90 , pp. 227-244
    • Shimodaira, H.1
  • 59
    • 0001861435 scopus 로고
    • Some remarks on Bézout's theorem and complexity theory
    • Springer Berlin 10.1007/978-1-4612-2740-3-40
    • Shub, M. (1993). Some remarks on Bézout's theorem and complexity theory. In From topology to computation: proceedings of the smalefest (pp. 443-455). Berlin: Springer.
    • (1993) From Topology to Computation: Proceedings of the Smalefest , pp. 443-455
    • Shub, M.1
  • 60
    • 0028516294 scopus 로고
    • Complexity of Bézout's theorem. V: Polynomial time
    • Shub, M., & Smale, S. (1994). Complexity of Bézout's theorem. V: polynomial time. Theoretical Computer Science, 133.
    • (1994) Theoretical Computer Science , pp. 133
    • Shub, M.1    Smale, S.2
  • 61
    • 0000675799 scopus 로고    scopus 로고
    • Complexity of Bézout's theorem. IV: Probability of success; Extensions
    • 1377247 0843.65035 10.1137/0733008
    • Shub, M., & Smale, S. (1996). Complexity of Bézout's theorem. IV: probability of success; extensions. SIAM Journal on Numerical Analysis, 33, 128-148.
    • (1996) SIAM Journal on Numerical Analysis , vol.33 , pp. 128-148
    • Shub, M.1    Smale, S.2
  • 62
    • 84855370082 scopus 로고    scopus 로고
    • Computationally efficient multi-task learning with least-squares probabilistic classifiers
    • 10.2197/ipsjtcva.3.1
    • Simm, J., Sugiyama, M., & Kato, T. (2011). Computationally efficient multi-task learning with least-squares probabilistic classifiers. IPSJ Transactions on Computer Vision and Applications, 3, 1-8.
    • (2011) IPSJ Transactions on Computer Vision and Applications , vol.3 , pp. 1-8
    • Simm, J.1    Sugiyama, M.2    Kato, T.3
  • 63
    • 84966209344 scopus 로고
    • The fundamental theorem of algebra and complexity theory
    • 590817 0456.12012 10.1090/S0273-0979-1981-14858-8
    • Smale, S. (1981). The fundamental theorem of algebra and complexity theory. Bulletin of the American Mathematical Society, 4, 1-36.
    • (1981) Bulletin of the American Mathematical Society , vol.4 , pp. 1-36
    • Smale, S.1
  • 65
    • 4243066295 scopus 로고    scopus 로고
    • Smoothed analysis of algorithms: Why the simplex algorithm usually takes polynomial time
    • 2145860 1192.90120 10.1145/990308.990310
    • Spielman, D. A., & Teng, S.-H. (2004). Smoothed analysis of algorithms: why the simplex algorithm usually takes polynomial time. Journal of the ACM, 51, 385-463.
    • (2004) Journal of the ACM , vol.51 , pp. 385-463
    • Spielman, D.A.1    Teng, S.-H.2
  • 67
    • 0010786475 scopus 로고    scopus 로고
    • On the influence of the kernel on the consistency of support vector machines
    • 1883281
    • Steinwart, I. (2001). On the influence of the kernel on the consistency of support vector machines. Journal of Machine Learning Research, 2, 67-93.
    • (2001) Journal of Machine Learning Research , vol.2 , pp. 67-93
    • Steinwart, I.1
  • 68
    • 77957851853 scopus 로고    scopus 로고
    • Superfast-trainable multi-class probabilistic classifier by least-squares posterior fitting
    • 93500 10.1587/transinf.E93.D.2690
    • Sugiyama, M. (2010). Superfast-trainable multi-class probabilistic classifier by least-squares posterior fitting. IEICE Transactions on Information and Systems, E93-D, 2690-2701.
    • (2010) IEICE Transactions on Information and Systems , pp. 2690-2701
    • Sugiyama, M.1
  • 70
    • 34249027984 scopus 로고    scopus 로고
    • Input-dependent estimation of generalization error under covariate shift
    • 2255627 1117.62069 10.1524/stnd.2005.23.4.249
    • Sugiyama, M., & Müller, K.-R. (2005). Input-dependent estimation of generalization error under covariate shift. Statistics & Decisions, 23, 249-279.
    • (2005) Statistics & Decisions , vol.23 , pp. 249-279
    • Sugiyama, M.1    Müller, K.-R.2
  • 73
    • 85161964516 scopus 로고    scopus 로고
    • Direct importance estimation with model selection and its application to covariate shift adaptation
    • 20 MIT Press Cambridge
    • Sugiyama, M., Nakajima, S., Kashima, H., von Bünau, P., & Kawanabe, M. (2008a). Direct importance estimation with model selection and its application to covariate shift adaptation. In Advances in neural information processing systems (Vol. 20, pp. 1433-1440). Cambridge: MIT Press.
    • (2008) Advances in Neural Information Processing Systems , pp. 1433-1440
    • Sugiyama, M.1    Nakajima, S.2    Kashima, H.3    Von Bünau, P.4    Kawanabe, M.5
  • 79
    • 84865400174 scopus 로고    scopus 로고
    • Density ratio matching under the Bregman divergence: A unified framework of density ratio estimation
    • 2960956 06118527 10.1007/s10463-011-0343-8
    • Sugiyama, M., Suzuki, T., & Kanamori, T. (2012a). Density ratio matching under the Bregman divergence: A unified framework of density ratio estimation. Annals of the Institute of Statistical Mathematics, 64, 1009-1044.
    • (2012) Annals of the Institute of Statistical Mathematics , vol.64 , pp. 1009-1044
    • Sugiyama, M.1    Suzuki, T.2    Kanamori, T.3
  • 81
    • 78650608280 scopus 로고    scopus 로고
    • Least-squares independent component analysis
    • 2768278 1205.94040 10.1162/NECO-a-00062
    • Suzuki, T., & Sugiyama, M. (2011). Least-squares independent component analysis. Neural Computation, 23, 284-301.
    • (2011) Neural Computation , vol.23 , pp. 284-301
    • Suzuki, T.1    Sugiyama, M.2
  • 83
    • 60849121715 scopus 로고    scopus 로고
    • Mutual information estimation reveals global associations between stimuli and biological processes
    • S52 10.1186/1471-2105-10-S1-S52
    • Suzuki, T., Sugiyama, M., Kanamori, T., & Sese, J. (2009a). Mutual information estimation reveals global associations between stimuli and biological processes. BMC Bioinformatics, 10, S52.
    • (2009) BMC Bioinformatics , vol.10
    • Suzuki, T.1    Sugiyama, M.2    Kanamori, T.3    Sese, J.4
  • 86
    • 0003079802 scopus 로고    scopus 로고
    • Characterizations, bounds, and probabilistic analysis of two complexity measures for linear programming problems
    • 1819786 0978.90069 10.1007/PL00011420
    • Todd, M. J., Tunçel, L., & Ye, Y. (2001). Characterizations, bounds, and probabilistic analysis of two complexity measures for linear programming problems. Mathematical Programming, 90, 59-69.
    • (2001) Mathematical Programming , vol.90 , pp. 59-69
    • Todd, M.J.1    Tunçel, L.2    Ye, Y.3
  • 88
    • 38749108479 scopus 로고    scopus 로고
    • Beyond Hirsch conjecture: Walks on random polytopes and smoothed complexity of the simplex method
    • 10.1109/FOCS.2006.19
    • Vershynin, R. (2006). Beyond Hirsch conjecture: walks on random polytopes and smoothed complexity of the simplex method. In FOCS 2006 (47th annual symposium on foundations of computer science (pp. 133-142).
    • (2006) FOCS 2006 (47th Annual Symposium on Foundations of Computer Science , pp. 133-142
    • Vershynin, R.1
  • 90
    • 77958598373 scopus 로고    scopus 로고
    • Dependence minimizing regression with model selection for non-linear causal inference under non-Gaussian noise
    • AAAI Press Atlanta
    • Yamada, M., & Sugiyama, M. (2010). Dependence minimizing regression with model selection for non-linear causal inference under non-Gaussian noise. In Proceedings of the twenty-fourth AAAI conference on artificial intelligence (AAAI2010) (pp. 643-648). Atlanta: AAAI Press.
    • (2010) Proceedings of the Twenty-fourth AAAI Conference on Artificial Intelligence (AAAI2010) , pp. 643-648
    • Yamada, M.1    Sugiyama, M.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.