메뉴 건너뛰기




Volumn 169, Issue 2, 2016, Pages 388-406

Stochastic Forward–Backward Splitting for Monotone Inclusions

Author keywords

Forward backward splitting algorithm; Monotone inclusions; Stochastic Fej r sequences; Stochastic first order methods

Indexed keywords

NUMERICAL ANALYSIS;

EID: 84964211787     PISSN: 00223239     EISSN: 15732878     Source Type: Journal    
DOI: 10.1007/s10957-016-0893-2     Document Type: Article
Times cited : (61)

References (62)
  • 1
    • 84972488065 scopus 로고
    • Monotone (nonlinear) operators in Hilbert space
    • Minty, G.J.: Monotone (nonlinear) operators in Hilbert space. Duke Math. J. 29, 341–346 (1962)
    • (1962) Duke Math. J. , vol.29 , pp. 341-346
    • Minty, G.J.1
  • 2
    • 85007556444 scopus 로고
    • Opérateurs maximaux monotones et semi-groupes de contractions dans les espaces de Hilbert. North-Holland Publishing Co., Amsterdam-London; American Elsevier Publishing Co., Inc
    • Brézis, H.: Opérateurs maximaux monotones et semi-groupes de contractions dans les espaces de Hilbert. North-Holland Publishing Co., Amsterdam-London; American Elsevier Publishing Co., Inc., New York (1973)
    • (1973) New York
    • Brézis, H.1
  • 6
    • 84972582929 scopus 로고
    • On the maximal monotonicity of subdifferential mappings
    • Rockafellar, R.T.: On the maximal monotonicity of subdifferential mappings. Pacif. J. Math. 33, 209–216 (1970)
    • (1970) Pacif. J. Math. , vol.33 , pp. 209-216
    • Rockafellar, R.T.1
  • 8
    • 13244295576 scopus 로고    scopus 로고
    • Solving monotone inclusions via compositions of nonexpansive averaged operators
    • Combettes, P.L.: Solving monotone inclusions via compositions of nonexpansive averaged operators. Optimation 53(5–6), 475–504 (2004)
    • (2004) Optimation , vol.53 , Issue.5-6 , pp. 475-504
    • Combettes, P.L.1
  • 9
    • 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(6), 964–979 (1979)
    • (1979) SIAM J. Numer. Anal. , vol.16 , Issue.6 , pp. 964-979
    • Lions, P.L.1    Mercier, B.2
  • 10
    • 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(2), 383–390 (1979)
    • (1979) J. Math. Anal. Appl. , vol.72 , Issue.2 , pp. 383-390
    • Passty, G.B.1
  • 11
    • 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(1), 183–202 (2009)
    • (2009) SIAM J. Imaging Sci. , vol.2 , Issue.1 , pp. 183-202
    • Beck, A.1    Teboulle, M.2
  • 12
    • 84868678967 scopus 로고    scopus 로고
    • Variable metric quasi-Fejér monotonicity
    • Combettes, P.L., Vũ, B.C.: Variable metric quasi-Fejér monotonicity. Nonlinear Anal. 78, 17–31 (2013)
    • (2013) Nonlinear Anal. , vol.78 , pp. 17-31
    • Combettes, P.L.1    Vũ, B.C.2
  • 13
    • 30844438177 scopus 로고    scopus 로고
    • Signal recovery by proximal forward-backward splitting
    • (electronic)
    • Combettes, P.L., Wajs, V.R.: Signal recovery by proximal forward-backward splitting. Multiscale Model. Simul 4(4), 1168–1200 (2005). (electronic)
    • (2005) Multiscale Model. Simul , vol.4 , Issue.4 , pp. 1168-1200
    • Combettes, P.L.1    Wajs, V.R.2
  • 14
    • 67651063011 scopus 로고    scopus 로고
    • Gradient methods for minimizing composite objective function. CORE Discussion Paper 2007/76
    • Nesterov, Y.: Gradient methods for minimizing composite objective function. CORE Discussion Paper 2007/76, Catholic University of Louvain (2007)
    • (2007) Catholic University of Louvain
    • Nesterov, Y.1
  • 15
    • 84886247153 scopus 로고    scopus 로고
    • Accelerated and inexact forward-backward algorithms
    • Villa, S., Salzo, S., Baldassarre, L., Verri, A.: Accelerated and inexact forward-backward algorithms. SIAM J. Optim. 23(3), 1607–1633 (2013)
    • (2013) SIAM J. Optim. , vol.23 , Issue.3 , pp. 1607-1633
    • Villa, S.1    Salzo, S.2    Baldassarre, L.3    Verri, A.4
  • 16
    • 75249102673 scopus 로고    scopus 로고
    • Efficient online and batch learning using forward backward splitting
    • Duchi, J., Singer, Y.: Efficient online and batch learning using forward backward splitting. J. Mach. Learn. Res. 10, 2899–2934 (2009)
    • (2009) J. Mach. Learn. Res. , vol.10 , pp. 2899-2934
    • Duchi, J.1    Singer, Y.2
  • 19
    • 84875940432 scopus 로고    scopus 로고
    • Solving variational inequalities with stochastic mirror-prox algorithm
    • Juditsky, A., Nemirovski, A., Tauvel, C.: Solving variational inequalities with stochastic mirror-prox algorithm. Stoch. Syst. 1(1), 17–58 (2011)
    • (2011) Stoch. Syst. , vol.1 , Issue.1 , pp. 17-58
    • Juditsky, A.1    Nemirovski, A.2    Tauvel, C.3
  • 20
    • 51449092038 scopus 로고    scopus 로고
    • Stochastic approximation approaches to the stochastic variational inequality problem
    • Jiang, H., Xu, H.: Stochastic approximation approaches to the stochastic variational inequality problem. IEEE Trans. Automat. Control 53(6), 1462–1475 (2008)
    • (2008) IEEE Trans. Automat. Control , vol.53 , Issue.6 , pp. 1462-1475
    • Jiang, H.1    Xu, H.2
  • 21
    • 84874634574 scopus 로고    scopus 로고
    • Regularized iterative stochastic approximation methods for stochastic variational inequality problems
    • Koshal, J., Nedic, A., Shanbhag, U.V.: Regularized iterative stochastic approximation methods for stochastic variational inequality problems. IEEE Trans. Autom. Contrl. 58(3), 594–609 (2013)
    • (2013) IEEE Trans. Autom. Contrl. , vol.58 , Issue.3 , pp. 594-609
    • Koshal, J.1    Nedic, A.2    Shanbhag, U.V.3
  • 23
    • 0040314261 scopus 로고
    • On the method of generalized stochastic gradients and quasi-Fejér sequences
    • Ermol’ev, Y.M.: On the method of generalized stochastic gradients and quasi-Fejér sequences. Cybernetics 5(2), 208–220 (1969)
    • (1969) Cybernetics , vol.5 , Issue.2 , pp. 208-220
    • Ermol’ev, Y.M.1
  • 25
    • 70450197241 scopus 로고    scopus 로고
    • Robust stochastic approximation approach to stochastic programming
    • Nemirovski, A., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19(4), 1574–1609 (2008)
    • (2008) SIAM J. Optim. , vol.19 , Issue.4 , pp. 1574-1609
    • Nemirovski, A.1    Juditsky, A.2    Lan, G.3    Shapiro, A.4
  • 26
    • 84940391194 scopus 로고    scopus 로고
    • Stochastic quasi-Fejér block-coordinate fixed point iterations with random sweeping
    • Combettes, P.L., Pesquet, J.C.: Stochastic quasi-Fejér block-coordinate fixed point iterations with random sweeping. SIAM J. Optim. 25(2), 1221–1248 (2015)
    • (2015) SIAM J. Optim. , vol.25 , Issue.2 , pp. 1221-1248
    • Combettes, P.L.1    Pesquet, J.C.2
  • 27
    • 84964287980 scopus 로고    scopus 로고
    • Stochastic approximations and perturbations in forward-backward splitting for monotone operators
    • Combettes, P.L., Pesquet, J.C.: Stochastic approximations and perturbations in forward-backward splitting for monotone operators. Pure Appl. Funct. Anal. 1(1), 13–37 (2016)
    • (2016) Pure Appl. Funct. Anal. , vol.1 , Issue.1 , pp. 13-37
    • Combettes, P.L.1    Pesquet, J.C.2
  • 28
    • 84901193687 scopus 로고    scopus 로고
    • A sparsity preserving stochastic gradient methods for sparse regression
    • Lin, Q., Chen, X., Peña, J.: A sparsity preserving stochastic gradient methods for sparse regression. Comput. Optim. Appl. 58, 455–482 (2014)
    • (2014) Comput. Optim. Appl. , vol.58 , pp. 455-482
    • Lin, Q.1    Chen, X.2    Peña, J.3
  • 29
    • 0041356704 scopus 로고
    • Fonctions convexes duales et points proximaux dans un espace hilbertien
    • Moreau, J.J.: Fonctions convexes duales et points proximaux dans un espace hilbertien. C. R. Acad. Sci. Paris 255, 2897–2899 (1962)
    • (1962) C. R. Acad. Sci. Paris , vol.255 , pp. 2897-2899
    • Moreau, J.J.1
  • 30
    • 84964205356 scopus 로고
    • The convergence of random quasi-Féjer sequences
    • Ermol’ev, J.M.: The convergence of random quasi-Féjer sequences. Kibernetika (Kiev) 4, 70–71 (1971)
    • (1971) Kibernetika (Kiev) , vol.4 , pp. 70-71
    • Ermol’ev, J.M.1
  • 31
    • 13244295576 scopus 로고    scopus 로고
    • Solving monotone inclusions via compositions of nonexpansive averaged operators
    • Combettes, P.L.: Solving monotone inclusions via compositions of nonexpansive averaged operators. Optimization 53, 475–504 (2004)
    • (2004) Optimization , vol.53 , pp. 475-504
    • Combettes, P.L.1
  • 32
    • 84856037674 scopus 로고    scopus 로고
    • Coupling forward-backward with penalty schemes and parallel splitting for constrained variational inequalities
    • Attouch, H., Czarnecki, M., Peypouquet, J.: Coupling forward-backward with penalty schemes and parallel splitting for constrained variational inequalities. SIAM J. Optim. 21(4), 1251–1274 (2011)
    • (2011) SIAM J. Optim. , vol.21 , Issue.4 , pp. 1251-1274
    • Attouch, H.1    Czarnecki, M.2    Peypouquet, J.3
  • 33
    • 84953706250 scopus 로고    scopus 로고
    • A stochastic inertial forward–backward splitting algorithm for multivariate monotone inclusions
    • Rosasco, L., Villa, S., Vũ, B.C.: A stochastic inertial forward–backward splitting algorithm for multivariate monotone inclusions. Optimization (2016)
    • (2016) Optimization
    • Rosasco, L.1    Villa, S.2    Vũ, B.C.3
  • 34
    • 0034389611 scopus 로고    scopus 로고
    • Gradient convergence in gradient methods with errors
    • (electronic)
    • Bertsekas, D.P., Tsitsiklis, J.N.: Gradient convergence in gradient methods with errors. SIAM J. Optim. 10(3), 627–642 (2000). (electronic)
    • (2000) SIAM J. Optim. , vol.10 , Issue.3 , pp. 627-642
    • Bertsekas, D.P.1    Tsitsiklis, J.N.2
  • 36
    • 38549116701 scopus 로고    scopus 로고
    • Hilbert-valued perturbed subgradient algorithms
    • Barty, K., Roy, J.S., Strugarek, C.: Hilbert-valued perturbed subgradient algorithms. Math. Oper. Res. 32(3), 551–562 (2007)
    • (2007) Math. Oper. Res. , vol.32 , Issue.3 , pp. 551-562
    • Barty, K.1    Roy, J.S.2    Strugarek, C.3
  • 37
    • 0003424464 scopus 로고
    • Masson, Paris, New York, Barcelona
    • Auslender, A.: Optimisation. Masson, Paris, New York, Barcelona (1976)
    • (1976) Optimisation
    • Auslender, A.1
  • 40
    • 84865693836 scopus 로고    scopus 로고
    • Stochastic variational inequalities:residual minimization smoothing sample average approximations
    • Chen, X., Wets, R.J.B., Zhang, Y.: Stochastic variational inequalities:residual minimization smoothing sample average approximations. SIAM J. Optim. 22(2), 649–673 (2012)
    • (2012) SIAM J. Optim. , vol.22 , Issue.2 , pp. 649-673
    • Chen, X.1    Wets, R.J.B.2    Zhang, Y.3
  • 42
    • 84892269424 scopus 로고
    • Nonlinear monotone operators and convex sets in Banach spaces
    • Browder, F.E.: Nonlinear monotone operators and convex sets in Banach spaces. Bull. Am. Math. Soc. 71, 780–785 (1965)
    • (1965) Bull. Am. Math. Soc. , vol.71 , pp. 780-785
    • Browder, F.E.1
  • 44
    • 84862273593 scopus 로고    scopus 로고
    • An optimal method for stochastic composite optimization
    • Lan, G.: An optimal method for stochastic composite optimization. Math. Prog. 133(1–2, Ser. A), 365–397 (2012)
    • (2012) Math. Prog. , vol.133 , Issue.1–2, Ser. A , pp. 365-397
    • Lan, G.1
  • 47
    • 78649396336 scopus 로고    scopus 로고
    • Dual averaging methods for regularized stochastic learning and online optimization
    • Xiao, L.: Dual averaging methods for regularized stochastic learning and online optimization. J. Mach. Learn. Res. 11, 2543–2596 (2010)
    • (2010) J. Mach. Learn. Res. , vol.11 , pp. 2543-2596
    • Xiao, L.1
  • 48
    • 17444425307 scopus 로고    scopus 로고
    • Online learning for very large data sets
    • Bottou, L., Le Cun, Y.: Online learning for very large data sets. Appl. Stoch. Models Bus. 21(2), 137–151 (2005)
    • (2005) Appl. Stoch. Models Bus. , vol.21 , Issue.2 , pp. 137-151
    • Bottou, L.1    Le Cun, Y.2
  • 50
    • 56449110590 scopus 로고    scopus 로고
    • SVM optimization: inverse dependence on training set size
    • Shalev-Shwartz, S., Srebro, N.: SVM optimization: inverse dependence on training set size. In: Proceedings ICML (2008)
    • (2008) Proceedings ICML
    • Shalev-Shwartz, S.1    Srebro, N.2
  • 51
    • 84863420367 scopus 로고    scopus 로고
    • Multi-stage convex relaxation for learning with sparse regularization
    • Zhang, T.: Multi-stage convex relaxation for learning with sparse regularization. In: Advances in Neural Information Processing Systems, pp. 1929–1936 (2008)
    • (2008) Advances in Neural Information Processing Systems , pp. 1929-1936
    • Zhang, T.1
  • 52
    • 84355162114 scopus 로고    scopus 로고
    • On stochastic gradient and subgradient methods with adaptive steplength sequences
    • Yousefian, F., Nedić, A., Shanbhag, U.V.: On stochastic gradient and subgradient methods with adaptive steplength sequences. Autom. J. IFAC 48(1), 56–67 (2012)
    • (2012) Autom. J. IFAC , vol.48 , Issue.1 , pp. 56-67
    • Yousefian, F.1    Nedić, A.2    Shanbhag, U.V.3
  • 53
    • 84871576447 scopus 로고    scopus 로고
    • Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization i: a generic algorithmic framework
    • Ghadimi, S., Lan, G.: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization i: a generic algorithmic framework. SIAM J. Optim. 22(4), 1469–1492 (2012)
    • (2012) SIAM J. Optim. , vol.22 , Issue.4 , pp. 1469-1492
    • Ghadimi, S.1    Lan, G.2
  • 54
    • 84892856128 scopus 로고    scopus 로고
    • Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization ii: shrinking procedures and optimal algorithms
    • Ghadimi, S., Lan, G.: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization ii: shrinking procedures and optimal algorithms. SIAM J. Optim. 23(4), 2061–2089 (2013)
    • (2013) SIAM J. Optim. , vol.23 , Issue.4 , pp. 2061-2089
    • Ghadimi, S.1    Lan, G.2
  • 55
    • 84907359690 scopus 로고    scopus 로고
    • Beyond the regret minimization barrier:optimal algorithms for stochastic strongly-convex optimization
    • Hazan, E., Kale, S.: Beyond the regret minimization barrier:optimal algorithms for stochastic strongly-convex optimization. J. Mach. Learn. Res. 15, 2489–2512 (2014)
    • (2014) J. Mach. Learn. Res. , vol.15 , pp. 2489-2512
    • Hazan, E.1    Kale, S.2
  • 56
    • 84964251369 scopus 로고    scopus 로고
    • Deterministic and stochastic primal-dual subgradient methods for minimizing uniformly convex functions
    • Juditsky, A., Nesterov, Y.E.: Deterministic and stochastic primal-dual subgradient methods for minimizing uniformly convex functions. Stoch. Syst. 4(1), 44–80 (2014)
    • (2014) Stoch. Syst. , vol.4 , Issue.1 , pp. 44-80
    • Juditsky, A.1    Nesterov, Y.E.2
  • 57
    • 0002686402 scopus 로고
    • A convergence theorem for non negative almost supermartingales and some applications
    • Academic Press, New York
    • Robbins, H., Siegmund, D.: A convergence theorem for non negative almost supermartingales and some applications. In: Optimizing Methods in Statistics, pp. 233–257. Academic Press, New York (1971)
    • (1971) Optimizing Methods in Statistics , pp. 233-257
    • Robbins, H.1    Siegmund, D.2
  • 60
    • 0242332013 scopus 로고    scopus 로고
    • Asymptotic properties of some projection-based robbins-monro procedures in a Hilbert space
    • Chen, X., White, H.: Asymptotic properties of some projection-based robbins-monro procedures in a Hilbert space. Stud. Nonlinear Dyn. Econ. 6, 1–53 (2002)
    • (2002) Stud. Nonlinear Dyn. Econ. , vol.6 , pp. 1-53
    • Chen, X.1    White, H.2
  • 61
    • 84964293651 scopus 로고    scopus 로고
    • Almost sure convergence of a stochastic approximation process in a convex set
    • Bennar, A., Monnez, J.M.: Almost sure convergence of a stochastic approximation process in a convex set. Int. J. Appl. Math. 20(5), 713–722 (2007)
    • (2007) Int. J. Appl. Math. , vol.20 , Issue.5 , pp. 713-722
    • Bennar, A.1    Monnez, J.M.2
  • 62
    • 32544453236 scopus 로고    scopus 로고
    • Almost sure convergence of stochastic gradient processes with matrix step sizes
    • Monnez, J.M.: Almost sure convergence of stochastic gradient processes with matrix step sizes. Stat. Probab. Lett. 76(5), 531–536 (2006)
    • (2006) Stat. Probab. Lett. , vol.76 , Issue.5 , pp. 531-536
    • Monnez, J.M.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.