메뉴 건너뛰기




Volumn 11, Issue , 2010, Pages 713-741

A fast hybrid algorithm for large-scale ℓ1-regularized logistic regression

Author keywords

1 regularization; Fixed point continuation; Large scale; Logistic regression; Supervised learning

Indexed keywords

BENCHMARK DATA; COMPUTATIONALLY EFFICIENT; FEATURE SELECTION; FIXED POINT CONTINUATION; FIXED POINTS; GEOMETRIC RATES; GLOBAL CONVERGENCE; HIGH DIMENSIONS; HYBRID ALGORITHMS; INTERIOR POINT; LARGE-SCALE LOGISTICS; LINE SEARCHES; LINEAR RATE; LOGISTIC REGRESSIONS; LOSS OF ACCURACY; MACHINE-LEARNING; MATRIX VECTOR MULTIPLICATION; MEMORY EFFICIENT; NEURAL SIGNAL PROCESSING; NEWTON'S METHODS; NUMERICAL COMPARISON; OBJECTIVE FUNCTIONS; OPTIMIZATION TECHNIQUES; SECOND PHASE; UCI MACHINE LEARNING REPOSITORY;

EID: 77949503812     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article
Times cited : (64)

References (63)
  • 4
    • 33947416035 scopus 로고    scopus 로고
    • Near optimal signal recovery from random projections: Universal encoding strategies?
    • E.J. Candés and T. Tao. Near optimal signal recovery from random projections: Universal encoding strategies? IEEE Trans. Inform. Theory, 52(2):5406-5425, 2006.
    • (2006) IEEE Trans. Inform. Theory , vol.52 , Issue.2 , pp. 5406-5425
    • Candés, E.J.1    Tao, T.2
  • 5
    • 31744440684 scopus 로고    scopus 로고
    • Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information
    • E.J. Candés, J. Romberg, and T. Tao. Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inform. Theory, 52(2):489-509, 2006.
    • (2006) IEEE Trans. Inform. Theory , vol.52 , Issue.2 , pp. 489-509
    • Candés, E.J.1    Romberg, J.2    Tao, T.3
  • 7
    • 0000364765 scopus 로고
    • Robust modeling with erratic data
    • J.F. Claerbout and F. Muir. Robust modeling with erratic data. Geophysics, 38(5):826-844, 1973.
    • (1973) Geophysics , vol.38 , Issue.5 , pp. 826-844
    • Claerbout, J.F.1    Muir, F.2
  • 10
    • 0037418225 scopus 로고    scopus 로고
    • 1 minimization
    • D.L. Donoho and M. Elad. Optimally sparse representations in general nonorthogonal dictionaries by ℓ1 minimization. Proc. Nat'l Academy of Science, 100(5):2197-2202, 2003.
    • (2003) Proc. Nat'l Academy of Science , vol.100 , Issue.5 , pp. 2197-2202
    • Donoho, D.L.1    Elad, M.2
  • 11
    • 0035504028 scopus 로고    scopus 로고
    • Uncertainty principles and ideal atomic decomposition
    • D.L. Donoho and X. Huo. Uncertainty principles and ideal atomic decomposition. IEEE. Trans. Inform. Theory, 48(9):2845-2862, 2001.
    • (2001) IEEE. Trans. Inform. Theory , vol.48 , Issue.9 , pp. 2845-2862
    • Donoho, D.L.1    Huo, X.2
  • 12
    • 0026845575 scopus 로고
    • Signal recovery and the large sieve
    • D.L. Donoho and B.F. Logan. Signal recovery and the large sieve. SIAM J. Appl. Math., 52(2): 577-591, 1992.
    • (1992) SIAM J. Appl. Math. , vol.52 , Issue.2 , pp. 577-591
    • Donoho, D.L.1    Logan, B.F.2
  • 13
    • 0001616908 scopus 로고
    • Uncertainty principle and signal recovery
    • D.L. Donoho and P.B. Stark. Uncertainty principle and signal recovery. SIAM J. Appl. Math., 49(3): 906-931, 1989.
    • (1989) SIAM J. Appl. Math. , vol.49 , Issue.3 , pp. 906-931
    • Donoho, D.L.1    Stark, P.B.2
  • 20
    • 34548105186 scopus 로고    scopus 로고
    • Large-scale bayesian logistic regression for text categorization
    • A. Genkin, D.D. Lewis, and D. Madigan. Large-scale bayesian logistic regression for text categorization. Technometrics, 49(3):291-304, 2007.
    • (2007) Technometrics , vol.49 , Issue.3 , pp. 291-304
    • Genkin, A.1    Lewis, D.D.2    Madigan, D.3
  • 21
    • 26644448212 scopus 로고    scopus 로고
    • Cortical origins of response time variability during rapid discrimination of visual objects
    • A.D. Gerson, L.C. Parra, and P. Sajda. Cortical origins of response time variability during rapid discrimination of visual objects. Neuroimage, 28(2):342-353, 2005.
    • (2005) Neuroimage , vol.28 , Issue.2 , pp. 342-353
    • Gerson, A.D.1    Parra, L.C.2    Sajda, P.3
  • 24
    • 69649095451 scopus 로고    scopus 로고
    • Fixed-point continuation for ℓ1-minimization: Methodology and convergence
    • E. Hale, W. Yin, and Y. Zhang. Fixed-point continuation for ℓ1-minimization: methodology and convergence. SIAM J. Optimization, 19(3):1107-1130, 2008.
    • (2008) SIAM J. Optimization , vol.19 , Issue.3 , pp. 1107-1130
    • Hale, E.1    Yin, W.2    Zhang, Y.3
  • 26
    • 34547688865 scopus 로고    scopus 로고
    • 1-regularized logistic regression
    • K. Koh, S.-J. Kim, and S. Boyd. An interior-point method for large-scale ℓ1-regularized logistic regression. J. Machine Learning Research, 8:1519-1555, 2007.
    • (2007) J. Machine Learning Research , vol.8 , pp. 1519-1555
    • Koh, K.1    Kim, S.-J.2    Boyd, S.3
  • 30
    • 84876811202 scopus 로고    scopus 로고
    • Rcv1: A new benchmark collection for text categorization research
    • D.D. Lewis, Y. Yang, T.G. Rose, and F. Li. Rcv1: A new benchmark collection for text categorization research. J. Machine Learning Research, 5:361-397, 2004.
    • (2004) J. Machine Learning Research , vol.5 , pp. 361-397
    • Lewis, D.D.1    Yang, Y.2    Rose, T.G.3    Li, F.4
  • 31
    • 34548125448 scopus 로고    scopus 로고
    • Logistic regression for disease classification using microarray data: Model selection in a large p and small n case
    • J.G. Liao and K.V. Chin. Logistic regression for disease classification using microarray data: model selection in a large p and small n case. Bioinformatics, 23(15):1945-1951, 2007.
    • (2007) Bioinformatics , vol.23 , Issue.15 , pp. 1945-1951
    • Liao, J.G.1    Chin, K.V.2
  • 32
    • 34250091945 scopus 로고
    • Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
    • N. Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285-318, 1988.
    • (1988) Machine Learning , vol.2 , pp. 285-318
    • Littlestone, N.1
  • 33
    • 33847366224 scopus 로고    scopus 로고
    • Portfolio optimization with linear and fixed transaction costs
    • M. Lobo, M. Fazel, and S. Boyd. Portfolio optimization with linear and fixed transaction costs. Annals of Operations Research, 152(1):376-394, 2007.
    • (2007) Annals of Operations Research , vol.152 , Issue.1 , pp. 376-394
    • Lobo, M.1    Fazel, M.2    Boyd, S.3
  • 35
    • 33751240089 scopus 로고    scopus 로고
    • Bayesian multinomial logistic regression for author identification
    • D. Madigan, A. Genkin, D. Lewis, and D Fradkin. Bayesian multinomial logistic regression for author identification. In Maxent Conference, pages 509-516, 2005.
    • (2005) Maxent Conference , pp. 509-516
    • Madigan, D.1    Genkin, A.2    Lewis, D.3    Fradkin, D.4
  • 36
    • 0029291966 scopus 로고
    • Sparse approximate solutions to linear system
    • B.K. Natarajan. Sparse approximate solutions to linear system. SIAMJ. Computing, 24(2):227-234, 1995.
    • (1995) SIAMJ. Computing , vol.24 , Issue.2 , pp. 227-234
    • Natarajan, B.K.1
  • 37
    • 14344249889 scopus 로고    scopus 로고
    • 2 regularization, and rotational invariance
    • ACM Press, New York
    • A. Ng. Feature selection, ℓ1 vs ℓ2 regularization, and rotational invariance. In International Conference on Machine Learning (ICML), pages 78-85. ACM Press, New York, 2004.
    • (2004) International Conference on Machine Learning (ICML) , pp. 78-85
    • Ng, A.1
  • 38
    • 0013161560 scopus 로고    scopus 로고
    • On feature selection: Learning with exponentially many irrelevant features as training examples
    • A. Ng. On feature selection: Learning with exponentially many irrelevant features as training examples. In International Conference on Machine Learning (ICML), pages 404-412, 1998.
    • (1998) International Conference on Machine Learning (ICML) , pp. 404-412
    • Ng, A.1
  • 39
    • 77349126814 scopus 로고    scopus 로고
    • Fast linearized bregman iteration for compressive sensing and sparse denoising
    • S. Osher, Y. Mao, B. Dong, and W. Yin. Fast linearized bregman iteration for compressive sensing and sparse denoising. Communications in Mathematical Sciences, 8(1):93-111, 2010.
    • (2010) Communications in Mathematical Sciences , vol.8 , Issue.1 , pp. 93-111
    • Osher, S.1    Mao, Y.2    Dong, B.3    Yin, W.4
  • 40
    • 34547849507 scopus 로고    scopus 로고
    • 1 regularized path algorithm for generalized linear models
    • M.Y. Park and T. Hastie. ℓ1 regularized path algorithm for generalized linear models. J. R. Statist. Soc. B, 69:659-677, 2007.
    • (2007) J. R. Statist. Soc. B , vol.69 , pp. 659-677
    • Park, M.Y.1    Hastie, T.2
  • 42
    • 26644455601 scopus 로고    scopus 로고
    • Recipes for the linear analysis of EEG
    • L.C. Parra, C.D. Spence, A.D. Gerson, and P. Sajda. Recipes for the linear analysis of EEG. Neuroimage, 28(2):326-341, 2005.
    • (2005) Neuroimage , vol.28 , Issue.2 , pp. 326-341
    • Parra, L.C.1    Spence, C.D.2    Gerson, A.D.3    Sajda, P.4
  • 44
    • 33644928473 scopus 로고    scopus 로고
    • Temporal characterization of the neural correlates of perceptual decision making in the human brain
    • M.G. Philiastides and P. Sajda. Temporal characterization of the neural correlates of perceptual decision making in the human brain. Cereb Cortex, 16(4):509-518, 2006.
    • (2006) Cereb Cortex , vol.16 , Issue.4 , pp. 509-518
    • Philiastides, M.G.1    Sajda, P.2
  • 46
    • 1242263806 scopus 로고    scopus 로고
    • The generalized lasso
    • V. Roth. The generalized lasso. IEEE Tran. Neural Networks, 15(1):16-28, 2004.
    • (2004) IEEE Tran. Neural Networks , vol.15 , Issue.1 , pp. 16-28
    • Roth, V.1
  • 47
    • 44049111982 scopus 로고
    • Nonlinear total variation based noise removal algorithms
    • L. Rudin, S. Osher, and E. Fatemi. Nonlinear total variation based noise removal algorithms. Physica D, 60(1-4):259-268, 1992.
    • (1992) Physica D , vol.60 , Issue.1-4 , pp. 259-268
    • Rudin, L.1    Osher, S.2    Fatemi, E.3
  • 48
    • 38049108135 scopus 로고    scopus 로고
    • Fast optimization methods for l1 regularization: A comparative study and two new approaches
    • M. Schmidt, G. Fung, and R. Rosales. Fast optimization methods for l1 regularization: a comparative study and two new approaches. In European Conference on Machine Learning (ECML), pages 286-297, 2007.
    • (2007) European Conference on Machine Learning (ECML) , pp. 286-297
    • Schmidt, M.1    Fung, G.2    Rosales, R.3
  • 49
    • 84907734262 scopus 로고    scopus 로고
    • A nonlinear inverse scale space method for a convex multiplicative noise model
    • J. Shi and S. Osher. A nonlinear inverse scale space method for a convex multiplicative noise model. SIAM J. Imaging Sciences, 1(3):294-321, 2008.
    • (2008) SIAM J. Imaging Sciences , vol.1 , Issue.3 , pp. 294-321
    • Shi, J.1    Osher, S.2
  • 52
    • 0001770611 scopus 로고
    • Deconvolution with the ℓ1 norm
    • H.L. Taylor, S.C. Banks, and J.F. McCoy. Deconvolution with the ℓ1 norm. Geophysics, 44(1): 39-52, 1979.
    • (1979) Geophysics , vol.44 , Issue.1 , pp. 39-52
    • Taylor, H.L.1    Banks, S.C.2    McCoy, J.F.3
  • 53
    • 85194972808 scopus 로고    scopus 로고
    • Regression shrinkage and selection via the lasso
    • R. Tibshirani. Regression shrinkage and selection via the lasso. J. Roy. Stat. Soc. B, 58(1):267-288, 1996.
    • (1996) J. Roy. Stat. Soc. B , vol.58 , Issue.1 , pp. 267-288
    • Tibshirani, R.1
  • 54
    • 35748966977 scopus 로고    scopus 로고
    • Learning string similarity measures for gene/protein name dictionary look-up using logistic regression
    • Y. Tsuruoka, J. McNaught, J. Tsujii, and S. Ananiadou. Learning string similarity measures for gene/protein name dictionary look-up using logistic regression. Bioinformatics, 23(20):2768-2774, 2007.
    • (2007) Bioinformatics , vol.23 , Issue.20 , pp. 2768-2774
    • Tsuruoka, Y.1    McNaught, J.2    Tsujii, J.3    Ananiadou, S.4
  • 60
    • 84977895355 scopus 로고    scopus 로고
    • 1-minimization with applications to compressed sensing
    • W. Yin, S. Osher, J. Darbon, and D. Goldfarb. Bregman iterative algorithm for ℓ1-minimization with applications to compressed sensing. SIAM J. Imaging Science, 1(1):143-168, 2008.
    • (2008) SIAM J. Imaging Science , vol.1 , Issue.1 , pp. 143-168
    • Yin, W.1    Osher, S.2    Darbon, J.3    Goldfarb, D.4
  • 61
    • 33845263263 scopus 로고    scopus 로고
    • On model selection consistency of lasso
    • P. Zhao and B. Yu. On model selection consistency of lasso. J. Machine Learning Research, 7: 2541-2567, 2007.
    • (2007) J. Machine Learning Research , vol.7 , pp. 2541-2567
    • Zhao, P.1    Yu, B.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.