메뉴 건너뛰기




Volumn , Issue PART 3, 2013, Pages 2158-2166

O(logT) projections for stochastic optimization of smooth and strongly convex functions

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; FUNCTIONS; LEARNING SYSTEMS; OPTIMIZATION; STOCHASTIC SYSTEMS;

EID: 84897492359     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (11)

References (35)
  • 1
    • 84860244324 scopus 로고    scopus 로고
    • Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization
    • Agarwal, A., Bartlett, P.L., P.Ravikumar, and Wainwright, M.J. Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization. IEEE Trans. Inf. Theory, 58(5):3235-3249, 2012.
    • (2012) IEEE Trans. Inf. Theory , vol.58 , Issue.5 , pp. 3235-3249
    • Agarwal, A.1    Bartlett, P.L.2    Ravikumar, P.3    Wainwright, M.J.4
  • 2
    • 26444592981 scopus 로고    scopus 로고
    • Local rademacher complexities
    • DOI 10.1214/009053605000000282
    • Bartlett, P.L., Bousquet, O., and Mendelson, S. Local rademacher complexities. Ann. Stat., 33(4):1497-1537, 2005. (Pubitemid 41423979)
    • (2005) Annals of Statistics , vol.33 , Issue.4 , pp. 1497-1537
    • Bartlett, P.L.1    Bousquet, O.2    Mendelson, S.3
  • 4
    • 79955702502 scopus 로고    scopus 로고
    • LIBSVM: A library for support vector machines
    • Chang, C. and Lin, C. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol., 2 (3):27:1-27:27, 2011.
    • (2011) ACM Trans. Intell. Syst. Technol. , vol.2 , Issue.3
    • Chang, C.1    Lin, C.2
  • 5
    • 84877732752 scopus 로고    scopus 로고
    • Optimal regularized dual averaging methods for stochastic optimization
    • Chen, X., Lin, Q., and Pena, J. Optimal regularized dual averaging methods for stochastic optimization. In NIPS 25, pp. 404-412, 2012.
    • (2012) NIPS 25 , pp. 404-412
    • Chen, X.1    Lin, Q.2    Pena, J.3
  • 6
    • 77956546378 scopus 로고    scopus 로고
    • Coresets, sparse greedy approximation, and the frank-wolfe algorithm
    • Clarkson, K.L. Coresets, sparse greedy approximation, and the frank-wolfe algorithm. ACM Trans. Algorithms, 6 (4):63:1-63:30, 2010.
    • (2010) ACM Trans. Algorithms , vol.6 , Issue.4
    • Clarkson, K.L.1
  • 7
    • 85162498265 scopus 로고    scopus 로고
    • Better mini-batch algorithms via accelerated gradient methods
    • Cotter, A., Shamir, O., Srebro, N., and Sridharan, K. Better mini-batch algorithms via accelerated gradient methods. In NIPS 24, pp. 1647-1655, 2011.
    • (2011) NIPS 24 , pp. 1647-1655
    • Cotter, A.1    Shamir, O.2    Srebro, N.3    Sridharan, K.4
  • 8
    • 80053446822 scopus 로고    scopus 로고
    • Optimal distributed online prediction
    • Getoor, Lise and Scheffer, Tobias (eds.)
    • Dekel, O., Gilad-Bachrach, R., Shamir, O., and Xiao, L. Optimal distributed online prediction. In Getoor, Lise and Scheffer, Tobias (eds.), ICML, pp. 713-720, 2011.
    • (2011) ICML , pp. 713-720
    • Dekel, O.1    Gilad-Bachrach, R.2    Shamir, O.3    Xiao, L.4
  • 10
  • 11
    • 84871576447 scopus 로고    scopus 로고
    • Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization i: A generic algorithmic framework
    • Ghadimi, S. and 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
  • 12
    • 43049120013 scopus 로고    scopus 로고
    • Sparse approximate solutions to semidefinite programs
    • Hazan, E. Sparse approximate solutions to semidefinite programs. In LATIN, pp. 306-316, 2008.
    • (2008) LATIN , pp. 306-316
    • Hazan, E.1
  • 13
    • 84898471955 scopus 로고    scopus 로고
    • Beyond the regret minimization barrier: An optimal algorithm for stochastic strongly-convex optimization
    • Hazan, E. and Kale, S. Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization. In COLT, pp. 421-436, 2011.
    • (2011) COLT , pp. 421-436
    • Hazan, E.1    Kale, S.2
  • 14
    • 84867122248 scopus 로고    scopus 로고
    • Projection-free online learning
    • Hazan, E. and Kale, S. Projection-free online learning. In ICML, pp. 521-528, 2012.
    • (2012) ICML , pp. 521-528
    • Hazan, E.1    Kale, S.2
  • 15
    • 77956508892 scopus 로고    scopus 로고
    • Accelerated gradient methods for stochastic optimization and online learning
    • Hu, C., Kwok, J., and Pan, W. Accelerated gradient methods for stochastic optimization and online learning. In NIPS 22, pp. 781-789, 2009.
    • (2009) NIPS 22 , pp. 781-789
    • Hu, C.1    Kwok, J.2    Pan, W.3
  • 16
    • 84897524603 scopus 로고    scopus 로고
    • Revisiting frank-wolfe: Projection-free sparse convex optimization
    • Jaggi, M. Revisiting frank-wolfe: Projection-free sparse convex optimization. In ICML, 2013.
    • (2013) ICML
    • Jaggi, M.1
  • 17
    • 84863337530 scopus 로고    scopus 로고
    • Regularized distance metric learning: Theory and algorithm
    • Jin, R., Wang, S., and Zhou, Y. Regularized distance metric learning: Theory and algorithm. In NIPS 22, pp. 862-870, 2009.
    • (2009) NIPS 22 , pp. 862-870
    • Jin, R.1    Wang, S.2    Zhou, Y.3
  • 19
    • 84875940432 scopus 로고    scopus 로고
    • Solving variational inequalities with stochastic mirror-prox algorithm
    • Juditsky, A., Nemirovski, A., and Tauvel, C. Solving variational inequalities with stochastic mirror-prox algorithm. Stochastic Systems, 1(1):17-58, 2011.
    • (2011) Stochastic Systems , vol.1 , Issue.1 , pp. 17-58
    • Juditsky, A.1    Nemirovski, A.2    Tauvel, C.3
  • 20
    • 84880570692 scopus 로고    scopus 로고
    • Block-coordinate frank-wolfe optimization for structural svm
    • Lacoste-Julien, S., Jaggi, M., Schmidt, M., and Pletscher, P. Block-coordinate frank-wolfe optimization for structural svm. In ICML, 2013.
    • (2013) ICML
    • Lacoste-Julien, S.1    Jaggi, M.2    Schmidt, M.3    Pletscher, P.4
  • 21
    • 84862273593 scopus 로고    scopus 로고
    • An optimal method for stochastic composite optimization
    • Lan, G. An optimal method for stochastic composite optimization. Math. Program., 133:365-397, 2012.
    • (2012) Math. Program. , vol.133 , pp. 365-397
    • Lan, G.1
  • 23
    • 84877725845 scopus 로고    scopus 로고
    • Stochastic gradient descent with only one projection
    • Mahdavi, M., Yang, T., Jin, R., Zhu, S., and Yi, J. Stochastic gradient descent with only one projection. In NIPS 25, pp. 503-511, 2012.
    • (2012) NIPS 25 , pp. 503-511
    • Mahdavi, M.1    Yang, T.2    Jin, R.3    Zhu, S.4    Yi, J.5
  • 24
    • 14944353419 scopus 로고    scopus 로고
    • Prox-method with rate of convergence O(1/t) for variational inequalities with lipschitz continuous monotone operators and smooth convex-concave saddle point problems
    • DOI 10.1137/S1052623403425629
    • Nemirovski, A. Prox-method with rate of convergence o(1/t) for variational inequalities with lipschitz continuous monotone operators and smooth convex-concave saddle point problems. SIAM J. Optim., 15(1):229-251, 2005. (Pubitemid 40360669)
    • (2005) SIAM Journal on Optimization , vol.15 , Issue.1 , pp. 229-251
    • Nemirovski, A.1
  • 26
    • 70450197241 scopus 로고    scopus 로고
    • Robust stochastic approximation approach to stochastic programming
    • Nemirovski, A., Juditsky, A., Lan, G., and Shapiro, A. Robust stochastic approximation approach to stochastic programming. SIAM J. Optim., 19(4):1574-1609, 2009.
    • (2009) SIAM J. Optim. , vol.19 , Issue.4 , pp. 1574-1609
    • Nemirovski, A.1    Juditsky, A.2    Lan, G.3    Shapiro, A.4
  • 27
    • 77953098740 scopus 로고    scopus 로고
    • Introductory lectures on convex optimization: A basic course
    • Kluwer Academic Publishers
    • Nesterov, Y. Introductory lectures on convex optimization: a basic course, volume 87 of Applied optimization. Kluwer Academic Publishers, 2004.
    • (2004) Applied Optimization , vol.87
    • Nesterov, Y.1
  • 28
    • 17444406259 scopus 로고    scopus 로고
    • Smooth minimization of non-smooth functions
    • DOI 10.1007/s10107-004-0552-5
    • Nesterov, Y. Smooth minimization of non-smooth functions. Math. Program., 103(1):127-152, 2005. (Pubitemid 40537674)
    • (2005) Mathematical Programming , vol.103 , Issue.1 , pp. 127-152
    • Nesterov, Y.1
  • 30
    • 84867120686 scopus 로고    scopus 로고
    • Making gradient descent optimal for strongly convex stochastic optimization
    • Rakhlin, A., Shamir, O., and Sridharan, K. Making gradient descent optimal for strongly convex stochastic optimization. In ICML, pp. 449-456, 2012.
    • (2012) ICML , pp. 449-456
    • Rakhlin, A.1    Shamir, O.2    Sridharan, K.3
  • 31
    • 85162000799 scopus 로고    scopus 로고
    • Topmoumoute online natural gradient algorithm
    • Roux, N.L., Manzagol, P., and Bengio, Y. Topmoumoute online natural gradient algorithm. In NIPS 20, pp. 849-856, 2008.
    • (2008) NIPS 20 , pp. 849-856
    • Roux, N.L.1    Manzagol, P.2    Bengio, Y.3
  • 33
    • 79952748054 scopus 로고    scopus 로고
    • Pegasos: Primal estimated sub-gradient solver for svm
    • Shalev-Shwartz, S., Singer, Y., Srebro, N., and Cotter, A. Pegasos: primal estimated sub-gradient solver for svm. Math. Program., 127(1):3-30, 2011.
    • (2011) Math. Program. , vol.127 , Issue.1 , pp. 3-30
    • Shalev-Shwartz, S.1    Singer, Y.2    Srebro, N.3    Cotter, A.4
  • 34
    • 70449535860 scopus 로고    scopus 로고
    • Geometry on probability spaces
    • Smale, S. and Zhou, D. Geometry on probability spaces. Constr. Approx., 30:311-323, 2009.
    • (2009) Constr. Approx. , vol.30 , pp. 311-323
    • Smale, S.1    Zhou, D.2
  • 35
    • 14344259207 scopus 로고    scopus 로고
    • Solving large scale linear prediction problems using stochastic gradient descent algorithms
    • Zhang, T. Solving large scale linear prediction problems using stochastic gradient descent algorithms. In ICML, pp. 919-926, 2004.
    • (2004) ICML , pp. 919-926
    • Zhang, T.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.