메뉴 건너뛰기




Volumn 129, Issue 2, 2011, Pages 163-195

Incremental proximal methods for large scale convex optimization

Author keywords

Convex; Gradient method; Incremental method; Proximal algorithm

Indexed keywords

CONVEX; INCREMENTAL METHOD; LARGE-SCALE CONVEX OPTIMIZATION; PROXIMAL ALGORITHM; PROXIMAL METHODS; RATE OF CONVERGENCE; SINGLE COMPONENTS; SUBGRADIENT; SUBGRADIENT ITERATIONS;

EID: 81155150371     PISSN: 00255610     EISSN: 14364646     Source Type: Journal    
DOI: 10.1007/s10107-011-0472-0     Document Type: Article
Times cited : (349)

References (58)
  • 1
    • 39449100600 scopus 로고    scopus 로고
    • A convergent incremental gradient method with a constant step size
    • DOI 10.1137/040615961
    • Blatt, D., Hero, A.O., Gauchman, H.: A convergent incremental gradient method with a constant step size. SIAM J. Optim. 18, 29-51 (2008) (Pubitemid 351271319)
    • (2007) SIAM Journal on Optimization , vol.18 , Issue.1 , pp. 29-51
    • Blatt, D.1    Hero, A.O.2    Gauchman, H.3
  • 2
    • 0041573292 scopus 로고    scopus 로고
    • Hybrid projection-reflection method for phase retrieval
    • Bauschke, H.H., Combettes, P.L., Luke, D.R.: Hybrid projection-reflection method for phase retrieval. J. Opt. Soc. Am. 20, 1025-1034 (2003)
    • (2003) J. Opt. Soc. Am. , vol.20 , pp. 1025-1034
    • Bauschke, H.H.1    Combettes, P.L.2    Luke, D.R.3
  • 3
    • 33645751712 scopus 로고    scopus 로고
    • Extrapolation algorithm for affine-convex feasibility problems
    • DOI 10.1007/s11075-005-9010-6
    • Bauschke, H.H., Combettes, P.L., Kruk, S.G.: Extrapolation algorithm for affine-convex feasibility problems. Numer. Algorithms 41, 239-274 (2006) (Pubitemid 43550992)
    • (2006) Numerical Algorithms , vol.41 , Issue.3 , pp. 239-274
    • Bauschke, H.H.1    Combettes, P.L.2    Kruk, S.G.3
  • 4
    • 81155141537 scopus 로고    scopus 로고
    • The ordered subsets mirror descent optimization method and its use for the positron emission tomography reconstruction
    • Butnariu, D., Censor, Y., Reich, S. (eds.), Elsevier, Amsterdam, Netherlands
    • Ben-Tal, A., Margalit, T., Nemirovski, A.: The ordered subsets mirror descent optimization method and its use for the positron emission tomography reconstruction. In: Butnariu, D., Censor, Y., Reich, S. (eds.) Inherently Parallel Algorithms in Feasibility and Optimization and their Applications, Elsevier, Amsterdam, Netherlands (2001)
    • (2001) Inherently Parallel Algorithms in Feasibility and Optimization and their Applications
    • Ben-Tal, A.1    Margalit, T.2    Nemirovski, A.3
  • 8
    • 0034389611 scopus 로고    scopus 로고
    • Gradient convergence in gradient methods
    • Bertsekas, D.P., Tsitsiklis, J.N.: Gradient convergence in gradient methods. SIAM J. Optim. 10, 627-642 (2000)
    • (2000) SIAM J. Optim. , vol.10 , pp. 627-642
    • Bertsekas, D.P.1    Tsitsiklis, J.N.2
  • 9
    • 85014561619 scopus 로고    scopus 로고
    • A fast iterative shrinkage-thresholding algorithm for linear inverse problems
    • Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2, 183-202 (2009)
    • (2009) SIAM J. Imaging Sci. , vol.2 , pp. 183-202
    • Beck, A.1    Teboulle, M.2
  • 10
    • 84926076587 scopus 로고    scopus 로고
    • Gradient-based algorithms with applications to signal-recovery problems
    • Eldar, Y., Palomar, D. (eds.). Cambridge University Press, Cambridge
    • Beck, A., Teboulle, M.: Gradient-based algorithms with applications to signal-recovery problems. In: Eldar, Y., Palomar, D. (eds.) Convex Optimization in Signal Processing and Communications, pp. 42-88. Cambridge University Press, Cambridge (2010)
    • (2010) Convex Optimization in Signal Processing and Communications , pp. 42-88
    • Beck, A.1    Teboulle, M.2
  • 11
    • 81155141538 scopus 로고    scopus 로고
    • A unifying polyhedral approximation framework for convex optimization. In: Laboratory for Information and Decision Systems Report LIDS-P-2820. MIT
    • to appear
    • Bertsekas, D.P., Yu, H.: A unifying polyhedral approximation framework for convex optimization. In: Laboratory for Information and Decision Systems Report LIDS-P-2820. MIT (2009); SIAM J. Optim. (to appear)
    • (2009) SIAM J. Optim.
    • Bertsekas, D.P.1    Yu, H.2
  • 12
    • 0030303864 scopus 로고    scopus 로고
    • Incremental least squares methods and the extended Kalman filter
    • Bertsekas, D.P.: Incremental least squares methods and the extended Kalman filter. SIAM J. Optim 6, 807-822 (1996)
    • (1996) SIAM J. Optim , vol.6 , pp. 807-822
    • Bertsekas, D.P.1
  • 13
    • 0031285678 scopus 로고    scopus 로고
    • Hybrid incremental gradient method for least squares
    • Bertsekas, D.P.: Hybrid incremental gradient method for least squares. SIAM J. Optim. 7, 913-926 (1997)
    • (1997) SIAM J. Optim. , vol.7 , pp. 913-926
    • Bertsekas, D.P.1
  • 17
    • 36749005582 scopus 로고    scopus 로고
    • A new TwIST: Two-step iterative shrinkage/thresholding algorithms for image restoration
    • DOI 10.1109/TIP.2007.909319
    • Bioucas-Dias, J., Figueiredo, M.A.T.: A new TwIST: two-step iterative shrinkage thresholding algorithms for image restoration. IEEE Trans. Image Process. 16, 2992-3004 (2007) (Pubitemid 350201232)
    • (2007) IEEE Transactions on Image Processing , vol.16 , Issue.12 , pp. 2992-3004
    • Bioucas-Dias, J.M.1    Figueiredo, M.A.T.2
  • 18
    • 0032022704 scopus 로고    scopus 로고
    • Nonlinear wavelet image processing: Variational problems, compression, and noise removal through wavelet shrinkage
    • PII S1057714998017849
    • Chambolle, A., DeVore, R.A., Lee, N.Y., Lucier, B.J.: Nonlinear wavelet image processing: variational problems, compression, and noise removal through wavelet shrinkage. IEEE Trans. Image Process. 7, 319-335 (1998) (Pubitemid 128745350)
    • (1998) IEEE Transactions on Image Processing , vol.7 , Issue.3 , pp. 319-335
    • Chambolle, A.1    DeVore, R.A.2    Lee, N.-Y.3    Lucier, B.J.4
  • 19
    • 69649097714 scopus 로고    scopus 로고
    • Relaxed alternating projection methods
    • Cegielski, A., Suchocka, A.: Relaxed alternating projection methods. SIAM J. Optim. 19, 1093-1106 (2008)
    • (2008) SIAM J. Optim. , vol.19 , pp. 1093-1106
    • Cegielski, A.1    Suchocka, A.2
  • 20
    • 30844438177 scopus 로고    scopus 로고
    • Signal recovery by proximal forward-backward splitting
    • DOI 10.1137/050626090
    • Combettes, P.L., Wajs, V.R.: Signal recovery by proximal forward-backward splitting. Multiscale Model. Simul. 4, 1168-1200 (2005) (Pubitemid 44932287)
    • (2005) Multiscale Modeling and Simulation , vol.4 , Issue.4 , pp. 1168-1200
    • Combettes, P.L.1    Wajs, V.R.2
  • 21
    • 7044231546 scopus 로고    scopus 로고
    • An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
    • DOI 10.1002/cpa.20042
    • Daubechies, I., Defrise,M., Mol, C.D.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57, 1413-1457 (2004) (Pubitemid 39427442)
    • (2004) Communications on Pure and Applied Mathematics , vol.57 , Issue.11 , pp. 1413-1457
    • Daubechies, I.1    Defrise, M.2    De Mol, C.3
  • 22
    • 35148813504 scopus 로고    scopus 로고
    • Coordinate and subspace optimization methods for linear least squares with non-quadratic regularization
    • DOI 10.1016/j.acha.2007.02.002, PII S1063520307000188
    • Elad,M., Matalon, B., Zibulevsky, M.: Coordinate and subspace optimization methods for linear least squares with non-quadratic regularization. J. Appl. Comput. Harmon. Anal. 23, 346-367 (2007) (Pubitemid 47552874)
    • (2007) Applied and Computational Harmonic Analysis , vol.23 , Issue.3 , pp. 346-367
    • Elad, M.1    Matalon, B.2    Zibulevsky, M.3
  • 23
    • 0142200827 scopus 로고    scopus 로고
    • An EM algorithm for wavelet-based image restoration
    • Figueiredo, M.A.T., Nowak, R.D.: An EM algorithm for wavelet-based image restoration. IEEE Trans. Image Process. 12, 906-916 (2003)
    • (2003) IEEE Trans. Image Process. , vol.12 , pp. 906-916
    • Figueiredo, M.A.T.1    Nowak, R.D.2
  • 24
    • 39449126969 scopus 로고    scopus 로고
    • Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems
    • DOI 10.1109/JSTSP.2007.910281
    • Figueiredo, M.A.T., Nowak, R.D., Wright, S.J.: Gradient projection for sparse reconstruction: application to compressed sensing and other inverse problems. IEEE J. Sel. Top. Signal Process. 1, 586-597 (2007) (Pubitemid 351276802)
    • (2007) IEEE Journal on Selected Topics in Signal Processing , vol.1 , Issue.4 , pp. 586-597
    • Figueiredo, M.A.T.1    Nowak, R.D.2    Wright, S.J.3
  • 25
    • 33845708830 scopus 로고
    • The method of projection for finding the common point in convex sets
    • English Translation
    • Gubin, L.G., Polyak, B.T., Raik, E.V.: The method of projection for finding the common point in convex sets. U.S.S.R. Comput. Math. Phys. 7, 1-24 (English Translation) (1967)
    • (1967) U.S.S.R. Comput. Math. Phys. , vol.7 , pp. 1-24
    • Gubin, L.G.1    Polyak, B.T.2    Raik, E.V.3
  • 26
    • 84972990726 scopus 로고
    • A class of unconstrained minimization methods for neural network training
    • Grippo, L.: A class of unconstrained minimization methods for neural network training. Optim.Methods Softw. 4, 135-150 (1994)
    • (1994) Optim. Methods Softw. , vol.4 , pp. 135-150
    • Grippo, L.1
  • 27
    • 0001546764 scopus 로고    scopus 로고
    • Convergent on-line algorithms for supervised learning in neural networks
    • Grippo, L.: Convergent on-line algorithms for supervised learning in neural networks. IEEE Trans. Neural Netw. 11, 1284-1299 (2000)
    • (2000) IEEE Trans. Neural Netw. , vol.11 , pp. 1284-1299
    • Grippo, L.1
  • 28
    • 81155141534 scopus 로고    scopus 로고
    • Incremental subgradients for constrained convex optimization: A unified framework and new methods
    • Helou, E.S., De Pierro, A.R.: Incremental subgradients for constrained convex optimization: A unified framework and new methods. SIAM J. Optim. 20, 1547-1572 (2009)
    • (2009) SIAM J. Optim. , vol.20 , pp. 1547-1572
    • Helou, E.S.1    De Pierro, A.R.2
  • 29
    • 73249115078 scopus 로고    scopus 로고
    • A randomized incremental subgradientmethod for distributed optimization in networked systems
    • Johansson, B., Rabi, M., Johansson, M.: A randomized incremental subgradientmethod for distributed optimization in networked systems. SIAM J. Optim. 20, 1157-1170 (2009)
    • (2009) SIAM J. Optim. , vol.20 , pp. 1157-1170
    • Johansson, B.1    Rabi, M.2    Johansson, M.3
  • 30
    • 0001256023 scopus 로고
    • Decomposition into functions in the minimization problem
    • Kibardin, V.M.: Decomposition into functions in the minimization problem. Autom. Remote Control 40, 1311-1323 (1980)
    • (1980) Autom. Remote Control , vol.40 , pp. 1311-1323
    • Kibardin, V.M.1
  • 31
    • 4043072116 scopus 로고    scopus 로고
    • Convergence of approximate and incremental subgradient methods for convex optimization
    • DOI 10.1137/S1052623400376366
    • Kiwiel, K.C.: Convergence of approximate and incremental subgradient methods for convex optimization. SIAM J. Optim. 14, 807-840 (2004) (Pubitemid 39073314)
    • (2004) SIAM Journal on Optimization , vol.14 , Issue.3 , pp. 807-840
    • Kiwiel, K.C.1
  • 32
    • 0000345334 scopus 로고
    • Splitting algorithms for the sum of two nonlinear operators
    • Lions, P.L., Mercier, B.: Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16, 964-979 (1979)
    • (1979) SIAM J. Numer. Anal. , vol.16 , pp. 964-979
    • Lions, P.L.1    Mercier, B.2
  • 33
    • 81155141536 scopus 로고
    • On an iteration method in the problem of approximating a function from a finite number of observations
    • Litvakov, B.M.: On an iteration method in the problem of approximating a function from a finite number of observations. Avtom. Telemech. 4, 104-113 (1966)
    • (1966) Avtom. Telemech. , vol.4 , pp. 104-113
    • Litvakov, B.M.1
  • 34
    • 84973041797 scopus 로고
    • Analysis of an approximate gradient projection method with applications to the backpropagation algorithm
    • Luo, Z.Q., Tseng, P.: Analysis of an approximate gradient projection method with applications to the backpropagation algorithm. Optim. Methods Softw. 4, 85-101 (1994)
    • (1994) Optim. Methods Softw. , vol.4 , pp. 85-101
    • Luo, Z.Q.1    Tseng, P.2
  • 35
    • 0001518167 scopus 로고
    • On the convergence of the LMS algorithm with adaptive learning rate for linear feedforward networks
    • Luo, Z.Q.: On the convergence of the LMS algorithm with adaptive learning rate for linear feedforward networks. Neural Comput. 3, 226-245 (1991)
    • (1991) Neural Comput. , vol.3 , pp. 226-245
    • Luo, Z.Q.1
  • 36
    • 84972916837 scopus 로고
    • Serial and parallel backpropagation convergence via nonmonotone perturbed minimization
    • Mangasarian, O.L., Solodov, M.V.: Serial and parallel backpropagation convergence via nonmonotone perturbed minimization. Optim. Methods Softw. 4, 103-116 (1994)
    • (1994) Optim. Methods Softw. , vol.4 , pp. 103-116
    • Mangasarian, O.L.1    Solodov, M.V.2
  • 39
    • 0005422061 scopus 로고    scopus 로고
    • Convergence rate of the incremental subgradient algorithm
    • Uryasev, S., Pardalos, P.M. (eds.), Kluwer Academic Publishers, Dordrecht
    • Nedić, A., Bertsekas, D.P. : Convergence rate of the incremental subgradient algorithm. In: Uryasev, S., Pardalos, P.M. (eds.) Stochastic Optimization: Algorithms and Applications, Kluwer Academic Publishers, Dordrecht (2000)
    • (2000) Stochastic Optimization: Algorithms and Applications
    • Nedić, A.1    Bertsekas, D.P.2
  • 40
    • 0036342213 scopus 로고    scopus 로고
    • Incremental subgradientmethods for nondifferentiable optimization
    • Nedić, A., Bertsekas, D.P.: Incremental subgradientmethods for nondifferentiable optimization. SIAM J. Optim. 12, 109-138 (2001)
    • (2001) SIAM J. Optim. , vol.12 , pp. 109-138
    • Nedić, A.1    Bertsekas, D.P.2
  • 41
    • 77956393281 scopus 로고    scopus 로고
    • The effect of deterministic noise in subgradient methods
    • Nedić, A., Bertsekas, D.P.: The effect of deterministic noise in subgradient methods. Math. Program. Ser. A 125, 75-99 (2010)
    • (2010) Math. Program. Ser. A , vol.125 , pp. 75-99
    • Nedić, A.1    Bertsekas, D.P.2
  • 42
    • 81155155860 scopus 로고    scopus 로고
    • Random projection algorithms for convex minimization problems
    • University of Illinois Report, (to appear)
    • Nedić, A.: Random projection algorithms for convex minimization problems. University of Illinois Report (2010); Math. Program. J. (to appear)
    • (2010) Math. Program. J.
    • Nedić, A.1
  • 44
    • 64249136579 scopus 로고    scopus 로고
    • Acollaborative training algorithm for distributed learning
    • Predd, J.B.,Kulkarni, S.R., Poor, H.V.:Acollaborative training algorithm for distributed learning. IEEE Trans. Inf. Theory 55, 1856-1871 (2009)
    • (2009) IEEE Trans. Inf. Theory , vol.55 , pp. 1856-1871
    • Predd, J.B.1    Kulkarni, S.R.2    Poor, H.V.3
  • 45
    • 0000120615 scopus 로고
    • Ergodic convergence to a zero of the sum of monotone operators in Hilbert space
    • Passty, G.B.: Ergodic convergence to a zero of the sum of monotone operators in Hilbert space. J. Math. Anal. Appl. 72, 383-390 (1979)
    • (1979) J. Math. Anal. Appl. , vol.72 , pp. 383-390
    • Passty, G.B.1
  • 46
    • 70450201554 scopus 로고    scopus 로고
    • Incremental stochastic subgradient algorithms for convex optimization
    • Ram, S.S., Nedić, A., Veeravalli, V.V.: Incremental stochastic subgradient algorithms for convex optimization. SIAM J. Optim. 20, 691-717 (2009)
    • (2009) SIAM J. Optim. , vol.20 , pp. 691-717
    • Ram, S.S.1    Nedić, A.2    Veeravalli, V.V.3
  • 47
    • 78049361018 scopus 로고    scopus 로고
    • Distributed stochastic subgradient projection algorithms for convex optimization
    • Ram, S.S., Nedić, A., Veeravalli, V.V.: Distributed stochastic subgradient projection algorithms for convex optimization. J. Optim. Theory Appl. 147, 516-545 (2010)
    • (2010) J. Optim. Theory Appl. , vol.147 , pp. 516-545
    • Ram, S.S.1    Nedić, A.2    Veeravalli, V.V.3
  • 49
    • 17144419228 scopus 로고    scopus 로고
    • Quantized incremental algorithms for distributed optimization
    • DOI 10.1109/JSAC.2005.843546
    • Rabbat, M.G., Nowak, R.D.: Quantized incremental algorithms for distributed optimization. IEEE J Sel. Areas Commun 23, 798-808 (2005) (Pubitemid 40519634)
    • (2005) IEEE Journal on Selected Areas in Communications , vol.23 , Issue.4 , pp. 798-808
    • Rabbat, M.G.1    Nowak, R.D.2
  • 50
    • 0004267646 scopus 로고
    • Princeton University Press, Princeton
    • Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton (1970)
    • (1970) Convex Analysis
    • Rockafellar, R.T.1
  • 51
    • 0016985417 scopus 로고
    • Monotone operators and the proximal point algorithm
    • Rockafellar, R.T.: Monotone operators and the proximal point algorithm. SIAM J. Control Optim. 14, 877-898 (1976)
    • (1976) SIAM J. Control Optim. , vol.14 , pp. 877-898
    • Rockafellar, R.T.1
  • 52
    • 34547964973 scopus 로고    scopus 로고
    • Pegasos: Primal estimated subgradient solver for SVM
    • New York, N.Y.
    • Shalev-Shwartz, S., Singer, Y., Srebro, N., Cotter A.: Pegasos: primal estimated subgradient solver for SVM. In: ICML 07 pp. 807-814. New York, N.Y. (2007)
    • (2007) ICML 07 , pp. 807-814
    • Shalev-Shwartz, S.1    Singer, Y.2    Srebro, N.3    Cotter, A.4
  • 53
    • 0032345479 scopus 로고    scopus 로고
    • Error stability properties of generalized gradient-type algorithms
    • Solodov, M.V., Zavriev, S.K.: Error stability properties of generalized gradient-type algorithms. J. Opt. Theory Appl. 98, 663-680 (1998)
    • (1998) J. Opt. Theory Appl. , vol.98 , pp. 663-680
    • Solodov, M.V.1    Zavriev, S.K.2
  • 54
    • 0032186984 scopus 로고    scopus 로고
    • Incremental gradient algorithms with stepsizes bounded away from zero
    • Solodov, M.V.: Incremental gradient algorithms with stepsizes bounded away from zero. Comput. Optim. Appl. 11, 28-35 (1998)
    • (1998) Comput. Optim. Appl. , vol.11 , pp. 28-35
    • Solodov, M.V.1
  • 55
    • 0032222083 scopus 로고    scopus 로고
    • An incremental gradient(-projection) method with momentum term and adaptive stepsize rule
    • Tseng, P.: An incremental gradient(-projection) method with momentum term and adaptive stepsize rule. SIAM J. Optim. 8, 506-531 (1998)
    • (1998) SIAM J. Optim. , vol.8 , pp. 506-531
    • Tseng, P.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.