메뉴 건너뛰기




Volumn 17, Issue , 2016, Pages

On the influence of momentum acceleration on online learning

Author keywords

Convergence Rate; Heavy ball Method; Mean Square Error Analysis; Momentum Acceleration; Nesterov's Method; Online Learning; Stochastic Gradient

Indexed keywords

GRADIENT METHODS; MEAN SQUARE ERROR; MOMENTUM; OPTIMIZATION; RISK ASSESSMENT; STOCHASTIC SYSTEMS;

EID: 84995388336     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article
Times cited : (72)

References (58)
  • 1
    • 0033116881 scopus 로고    scopus 로고
    • Analysis of learning rate and momentum term in backpropagation neural network algorithm trained to predict pavement performance
    • N. O. Attoh-Okine. Analysis of learning rate and momentum term in backpropagation neural network algorithm trained to predict pavement performance. Advances in Engineering Software, 30(4):291-302, 1999.
    • (1999) Advances in Engineering Software , vol.30 , Issue.4 , pp. 291-302
    • Attoh-Okine, N.O.1
  • 2
    • 85014561619 scopus 로고    scopus 로고
    • A fast iterative shrinkage-thresholding algorithm for linear inverse problems
    • A. Beck and M. Teboulle. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences, 2(1):183-202, 2009.
    • (2009) SIAM Journal on Imaging Sciences , vol.2 , Issue.1 , pp. 183-202
    • Beck, A.1    Teboulle, M.2
  • 5
    • 84904136037 scopus 로고    scopus 로고
    • Large-scale machine learning with stochastic gradient descent
    • Springer, Paris, France
    • L. Bottou. Large-scale machine learning with stochastic gradient descent. In Proc. International Conference on Computational Statistics, pages 177-186. Springer, Paris, France, 2010.
    • (2010) Proc. International Conference on Computational Statistics , pp. 177-186
    • Bottou, L.1
  • 8
    • 85032752418 scopus 로고    scopus 로고
    • Convex optimization for big data: Scalable randomized, and parallel algorithms for big data analytics
    • V. Cevher, S. Becker, and M. Schmidt. Convex optimization for big data: Scalable, randomized, and parallel algorithms for big data analytics. IEEE Signal Processing Magazine, 31(5):32-43, 2014.
    • (2014) IEEE Signal Processing Magazine , vol.31 , Issue.5 , pp. 32-43
    • Cevher, V.1    Becker, S.2    Schmidt, M.3
  • 9
    • 57249107300 scopus 로고    scopus 로고
    • Smooth optimization with approximate gradient
    • A. d'Aspremont. Smooth optimization with approximate gradient. SIAM Journal on Optimization, 19(3):1171-1183, 2008.
    • (2008) SIAM Journal on Optimization , vol.19 , Issue.3 , pp. 1171-1183
    • D'Aspremont, A.1
  • 10
    • 84937908747 scopus 로고    scopus 로고
    • SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives
    • Montreal, Canada
    • A. Defazio, F. Bach, and S. Lacoste-Julien. SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives. In Proc. Advances in Neural Information Processing Systems, pages 1646-1654, Montreal, Canada, 2014.
    • (2014) Proc. Advances in Neural Information Processing Systems , pp. 1646-1654
    • Defazio, A.1    Bach, F.2    Lacoste-Julien, S.3
  • 11
    • 84905567870 scopus 로고    scopus 로고
    • First-order methods of smooth convex optimization with inexact oracle
    • O. Devolder, F. Glineur, and Y. Nesterov. First-order methods of smooth convex optimization with inexact oracle. Mathematical Programming, 146(1-2):37-75, 2014.
    • (2014) Mathematical Programming , vol.146 , Issue.1-2 , pp. 37-75
    • Devolder, O.1    Glineur, F.2    Nesterov, Y.3
  • 13
    • 80052250414 scopus 로고    scopus 로고
    • Adaptive subgradient methods for online learning and stochastic optimization
    • J. Duchi, E. Hazan, and Y. Singer. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(2):2121-2159, 2011.
    • (2011) Journal of Machine Learning Research , vol.12 , Issue.2 , pp. 2121-2159
    • Duchi, J.1    Hazan, E.2    Singer, Y.3
  • 14
    • 84984697477 scopus 로고    scopus 로고
    • From averaging to acceleration, there is only a step-size
    • N. Flammarion and F. Bach. From averaging to acceleration, there is only a step-size. Journal of Machine Learning Research, 40(1):1-38, 2015.
    • (2015) Journal of Machine Learning Research , vol.40 , Issue.1 , pp. 1-38
    • Flammarion, N.1    Bach, F.2
  • 16
    • 84871576447 scopus 로고    scopus 로고
    • Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization I: A generic algorithmic framework
    • S. Ghadimi and G. Lan. Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization I: A generic algorithmic framework. SIAM Journal on Optimization, 22(4):1469-1492, 2012.
    • (2012) SIAM Journal on Optimization , vol.22 , Issue.4 , pp. 1469-1492
    • Ghadimi, S.1    Lan, G.2
  • 18
    • 77956508892 scopus 로고    scopus 로고
    • Accelerated gradient methods for stochastic optimization and online learning
    • Vancouver, Canada
    • C. Hu, W. Pan, and J. T. Kwok. Accelerated gradient methods for stochastic optimization and online learning. In Proc. Advances in Neural Information Processing Systems, pages 781-789, Vancouver, Canada, 2009.
    • (2009) Proc. Advances in Neural Information Processing Systems , pp. 781-789
    • Hu, C.1    Pan, W.2    Kwok, J.T.3
  • 19
    • 84898963415 scopus 로고    scopus 로고
    • Accelerating stochastic gradient descent using predictive variance reduction
    • Lake Tahoe, Navada
    • R. Johnson and T. Zhang. Accelerating stochastic gradient descent using predictive variance reduction. In Proc. Advances in Neural Information Processing Systems (NIPS), pages 315-323, Lake Tahoe, Navada, 2013.
    • (2013) Proc. Advances in Neural Information Processing Systems (NIPS) , pp. 315-323
    • Johnson, R.1    Zhang, T.2
  • 22
    • 84862273593 scopus 로고    scopus 로고
    • An optimal method for stochastic composite optimization
    • G. Lan. An optimal method for stochastic composite optimization. Mathematical Programming, 133(1-2):365-397, 2012.
    • (2012) Mathematical Programming , vol.133 , Issue.1-2 , pp. 365-397
    • Lan, G.1
  • 23
    • 84962476790 scopus 로고    scopus 로고
    • Analysis and design of optimization algorithms via integral quadratic constraints
    • L. Lessard, B. Recht, and A. Packard. Analysis and design of optimization algorithms via integral quadratic constraints. SIAM Journal on Optimization, 26(1):57-95, 2016.
    • (2016) SIAM Journal on Optimization , vol.26 , Issue.1 , pp. 57-95
    • Lessard, L.1    Recht, B.2    Packard, A.3
  • 24
    • 0005422061 scopus 로고    scopus 로고
    • Convergence rate of incremental subgradient algorithms
    • S. Uryasey and M. Pardalos P, editors, Springer
    • A. Nedić and D. P. Bertsekas. Convergence rate of incremental subgradient algorithms. In S. Uryasey and M. Pardalos P, editors, Stochastic Optimization: Algorithms and Applications, volume 54, pages 223-264. Springer, 2001.
    • (2001) Stochastic Optimization: Algorithms and Applications , vol.54 , pp. 223-264
    • Nedić, A.1    Bertsekas, D.P.2
  • 25
    • 34548480020 scopus 로고
    • A method of solving a convex programming problem with convergence rate O(1/k2)
    • Y. Nesterov. A method of solving a convex programming problem with convergence rate O(1/k2). Soviet Mathematics Doklady, 27(2):372-376, 1983.
    • (1983) Soviet Mathematics Doklady , vol.27 , Issue.2 , pp. 372-376
    • Nesterov, Y.1
  • 27
    • 17444406259 scopus 로고    scopus 로고
    • Smooth minimization of non-smooth functions
    • Y. Nesterov. Smooth minimization of non-smooth functions. Mathematical Programming, 103(1):127-152, 2005.
    • (2005) Mathematical Programming , vol.103 , Issue.1 , pp. 127-152
    • Nesterov, Y.1
  • 28
    • 84937865260 scopus 로고    scopus 로고
    • Stochastic proximal gradient descent with acceleration techniques
    • Montreal, Canada
    • A. Nitanda. Stochastic proximal gradient descent with acceleration techniques. In Proc. Advances in Neural Information Processing Systems, pages 1574-1582, Montreal, Canada, 2014.
    • (2014) Proc. Advances in Neural Information Processing Systems , pp. 1574-1582
    • Nitanda, A.1
  • 31
    • 0016321936 scopus 로고
    • Channel identification for high speed digital communications
    • J. G. Proakis. Channel identification for high speed digital communications. IEEE Transactions on Automatic Control, 19(6):916-922, 1974.
    • (1974) IEEE Transactions on Automatic Control , vol.19 , Issue.6 , pp. 916-922
    • Proakis, J.G.1
  • 32
    • 0032983160 scopus 로고    scopus 로고
    • On the momentum term in gradient descent learning algorithms
    • N. Qian. On the momentum term in gradient descent learning algorithms. Neural Networks, 12(1):145-151, 1999.
    • (1999) Neural Networks , vol.12 , Issue.1 , pp. 145-151
    • Qian, N.1
  • 33
    • 84877725219 scopus 로고    scopus 로고
    • A stochastic gradient method with an exponential convergence rate for finite training sets
    • Lake Tahoe, Navada
    • N. L. Roux, M. Schmidt, and F. R. Bach. A stochastic gradient method with an exponential convergence rate for finite training sets. In Proc. Advances in Neural Information Processing Systems (NIPS), pages 2663-2671, Lake Tahoe, Navada, 2012.
    • (2012) Proc. Advances in Neural Information Processing Systems (NIPS) , pp. 2663-2671
    • Roux, N.L.1    Schmidt, M.2    Bach, F.R.3
  • 36
    • 84905009821 scopus 로고    scopus 로고
    • Adaptation, learning, and optimization over networks
    • Jul
    • A. H. Sayed. Adaptation, learning, and optimization over networks. Foundations and Trends in Machine Learning, 7(4-5):311-801, Jul. 2014a.
    • (2014) Foundations and Trends in Machine Learning , vol.7 , Issue.4-5 , pp. 311-801
    • Sayed, A.H.1
  • 37
    • 84897483887 scopus 로고    scopus 로고
    • Adaptive networks
    • A. H. Sayed. Adaptive networks. Proceedings of the IEEE, 102(4):460-497, 2014b.
    • (2014) Proceedings of the IEEE , vol.102 , Issue.4 , pp. 460-497
    • Sayed, A.H.1
  • 39
    • 84965174061 scopus 로고    scopus 로고
    • Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
    • Beijing, China
    • S. Shalev-Shwartz and T. Zhang. Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization. In Proc. International Conference on Machine Learning, pages 64-72, Beijing, China, 2014.
    • (2014) Proc. International Conference on Machine Learning , pp. 64-72
    • Shalev-Shwartz, S.1    Zhang, T.2
  • 45
    • 84937061485 scopus 로고    scopus 로고
    • Tracking performance of momentum LMS algorithm for a chirped sinusoidal signal
    • Tampere, Finland
    • L. K. Ting, C. F. N. Cowan, and R. F. Woods. Tracking performance of momentum LMS algorithm for a chirped sinusoidal signal. In Proc. European Signal Processing Conference, pages 1-4, Tampere, Finland, 2000.
    • (2000) Proc. European Signal Processing Conference , pp. 1-4
    • Ting, L.K.1    Cowan, C.F.N.2    Woods, R.F.3
  • 46
    • 0024749726 scopus 로고
    • Properties of the momentum LMS algorithm
    • M. A. Tugay and Y. Tanik. Properties of the momentum LMS algorithm. Signal Processing, 18(2):117-127, 1989.
    • (1989) Signal Processing , vol.18 , Issue.2 , pp. 117-127
    • Tugay, M.A.1    Tanik, Y.2
  • 50
    • 78649396336 scopus 로고    scopus 로고
    • Dual averaging methods for regularized stochastic learning and online optimization
    • (Oct)
    • L. Xiao. Dual averaging methods for regularized stochastic learning and online optimization. Journal of Machine Learning Research, 11(Oct):2543-2596, 2010.
    • (2010) Journal of Machine Learning Research , vol.11 , pp. 2543-2596
    • Xiao, L.1
  • 52
    • 84973369182 scopus 로고    scopus 로고
    • Performance limits of single-agent and multi-agent sub-gradient stochastic learning
    • Shanghai, China, March
    • B. Ying and A. H. Sayed. Performance limits of single-agent and multi-agent sub-gradient stochastic learning. In Proc. International Conference on Acoustics, Speech and Signal Processing, pages 4905-4909, Shanghai, China, March 2016.
    • (2016) Proc. International Conference on Acoustics, Speech and Signal Processing , pp. 4905-4909
    • Ying, B.1    Sayed, A.H.2
  • 55
    • 33749243068 scopus 로고    scopus 로고
    • Solving large scale linear prediction problems using stochastic gradient descent algorithms
    • Alberta, Canada
    • T. Zhang. Solving large scale linear prediction problems using stochastic gradient descent algorithms. In Proc. International Conference on Machine Learning, page 116, Alberta, Canada, 2004.
    • (2004) Proc. International Conference on Machine Learning , pp. 116
    • Zhang, T.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.