Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization (Q2515032): Difference between revisions

From MaRDI portal
Importer (talk | contribs)
Changed an Item
ReferenceBot (talk | contribs)
Changed an Item
Property / cites work
 
Property / cites work: Smoothing technique and its applications in semidefinite optimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Interior Gradient and Proximal Methods for Convex and Conic Optimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: NESTA: A Fast and Accurate First-Order Method for Sparse Recovery / rank
 
Normal rank
Property / cites work
 
Property / cites work: Lectures on Modern Convex Optimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Non-Euclidean restricted memory level method for large-scale convex optimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Newton's method for convex programming and Tschebyscheff approximation / rank
 
Normal rank
Property / cites work
 
Property / cites work: First-Order Methods for Sparse Covariance Selection / rank
 
Normal rank
Property / cites work
 
Property / cites work: First-order methods of smooth convex optimization with inexact oracle / rank
 
Normal rank
Property / cites work
 
Property / cites work: Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms / rank
 
Normal rank
Property / cites work
 
Property / cites work: Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Spectral Bundle Method for Semidefinite Programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: An optimal method for stochastic composite optimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: The Cutting-Plane Method for Solving Convex Programs / rank
 
Normal rank
Property / cites work
 
Property / cites work: An aggregate subgradient method for nonsmooth convex minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Proximity control in bundle methods for convex nondifferentiable minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Proximal level bundle methods for convex nondifferentiable optimization, saddle-point problems and variational inequalities / rank
 
Normal rank
Property / cites work
 
Property / cites work: Primal-dual first-order methods with \({\mathcal {O}(1/\varepsilon)}\) iteration-complexity for cone programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Validation analysis of mirror descent stochastic approximation method / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4132264 / rank
 
Normal rank
Property / cites work
 
Property / cites work: New variants of bundle methods / rank
 
Normal rank
Property / cites work
 
Property / cites work: A proximal method for composite minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Decomposition algorithms for stochastic programming on a computational grid / rank
 
Normal rank
Property / cites work
 
Property / cites work: The empirical behavior of sampling methods for stochastic programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Smooth Optimization Approach for Sparse Covariance Selection / rank
 
Normal rank
Property / cites work
 
Property / cites work: Monte Carlo bounding techniques for determinig solution quality in stochastic programs / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3967358 / rank
 
Normal rank
Property / cites work
 
Property / cites work: On parallel complexity of nonsmooth convex optimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Prox-Method with Rate of Convergence <i>O</i>(1/<i>t</i>) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems / rank
 
Normal rank
Property / cites work
 
Property / cites work: Robust Stochastic Approximation Approach to Stochastic Programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Optimal methods of smooth convex minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3809587 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Introductory lectures on convex optimization. A basic course. / rank
 
Normal rank
Property / cites work
 
Property / cites work: Excessive Gap Technique in Nonsmooth Convex Minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Smooth minimization of non-smooth functions / rank
 
Normal rank
Property / cites work
 
Property / cites work: Inexact Bundle Methods for Two-Stage Stochastic Programming / rank
 
Normal rank
Property / cites work
 
Property / cites work: Approximate level method for nonsmooth convex minimization / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3376534 / rank
 
Normal rank

Revision as of 16:06, 9 July 2024

scientific article
Language Label Description Also known as
English
Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization
scientific article

    Statements

    Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization (English)
    0 references
    0 references
    9 February 2015
    0 references
    The author considers is the convex programming problem (CP) \[ f^{\ast }:=\min_{x\in X}f\left( x\right) , \] where \(X\) is a convex compact set and \(f:X\rightarrow \mathbb{R}\) is a closed function. The author develops uniformly optimal first-order methods for (CP). By incorporating a multistep acceleration scheme into the well-known bundle-level method, he develops an accelerated bundle-level method, and shows that it can achieve the optimal complexity for solving a general class of black-box CP problems without requiring the input of any smoothness information. The author develops a more practical, restricted memory version of this method, namely the accelerated prox-level (APL) method. He investigate the generalization of this method, namely the USL method, for solving certain composite CP problems and an important class of saddle-point problems. Finally, the author shows the advantages of the APL and USL methods over some existing first-order methods for solving certain classes of semidefinite programming and stochastic programming problems.
    0 references
    convex programming
    0 references
    complexity
    0 references
    bundle-level
    0 references
    optimal methods
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references

    Identifiers

    0 references
    0 references
    0 references
    0 references
    0 references
    0 references