An optimal method for stochastic composite optimization

@article{Lan2012AnOM,
  title={An optimal method for stochastic composite optimization},
  author={G. Lan},
  journal={Mathematical Programming},
  year={2012},
  volume={133},
  pages={365-397}
}
  • G. Lan
  • Published 2012
  • Mathematics, Computer Science
  • Mathematical Programming
    • This paper considers an important class of convex programming (CP) problems, namely, the stochastic composite optimization (SCO), whose objective function is given by the summation of general nonsmooth and smooth stochastic components. Since SCO covers non-smooth, smooth and stochastic CP as certain special cases, a valid lower bound on the rate of convergence for solving these problems is known from the classic complexity theory of convex programming. Note however that the optimization… CONTINUE READING
    View on Springer
    optimization-online.org
    343 Citations
    Highly Influential Citations
    53
    Background Citations
    148
    Methods Citations
    156
    Results Citations
    16
    343 Citations
    Citation Type

    Citation Type

    Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms
    • 143
    • PDF
    Accelerated gradient methods for nonconvex nonlinear and stochastic programming
    • 353
    • PDF
    Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
    • 228
    • PDF
    General convergence analysis of stochastic first order methods for composite optimization
    • PDF
    Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
    • 646
    • PDF
    Level methods uniformly optimal for composite and structured nonsmooth convex optimization
    • 2
    • PDF
    The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle
    • 97
    • PDF
    Gradient sliding for composite optimization
    • G. Lan
    • Mathematics, Computer Science
    • Math. Program.
    • 2016
    • 33
    • PDF
    Bundle-type methods uniformly optimal for smooth and nonsmooth convex optimization ?
    • 5
    • PDF
    Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization
    • 76
    • PDF

    References

    SHOWING 1-10 OF 64 REFERENCES
    Robust Stochastic Approximation Approach to Stochastic Programming
    • 1,532
    • PDF
    SMOOTH OPTIMIZATION APPROACH FOR SPARSE COVARIANCE SELECTION∗
    • O SIAMJ.
    • 2009
    • 75
    • PDF
    Gradient methods for minimizing composite objective function
    • 1,223
    • Highly Influential
    • PDF
    Primal-dual subgradient methods for convex problems
    • Y. Nesterov
    • Mathematics, Computer Science
    • Math. Program.
    • 2009
    • 703
    • PDF
    Smoothing Technique and its Applications in Semidefinite Optimization
    • Y. Nesterov
    • Mathematics, Computer Science
    • Math. Program.
    • 2007
    • 154
    • PDF
    Iteration-complexity of first-order penalty methods for convex programming
    • 55
    • PDF
    Non-euclidean restricted memory level method for large-scale convex optimization
    • 101
    • PDF
    Primal-dual first-order methods with $${\mathcal {O}(1/\epsilon)}$$ iteration-complexity for cone programming
    • 61
    • PDF
    On the Complexity of the Hybrid Proximal Extragradient Method for the Iterates and the Ergodic Mean
    • 121
    • PDF
    Solving variational inequalities with Stochastic Mirror-Prox algorithm
    • 231
    • PDF