Generalized uniformly optimal methods for nonlinear programming

DOI10.1007/s10915-019-00915-4zbMath1418.90191arXiv1508.07384OpenAlexW2963843970WikidataQ128367525 ScholiaQ128367525MaRDI QIDQ2316202

Guanghui Lan, Hongchao Zhang, Saeed Ghadimi

Publication date: 26 July 2019

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1508.07384

zbMATH Keywords

nonconvex optimizationquasi-Newton methodsaccelerated gradient methodsaccelerated level methodsparameter free methodsuniformly optimal methods

Mathematics Subject Classification ID

Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Nonconvex programming, global optimization (90C26) Numerical methods based on nonlinear programming (49M37)

Related Items

Accelerated inexact composite gradient methods for nonconvex spectral optimization problems ⋮ Generalized mirror prox algorithm for monotone variational inequalities: Universality and inexact oracle ⋮ Primal–dual accelerated gradient methods with small-dimensional relaxation oracle ⋮ An efficient adaptive accelerated inexact proximal point method for solving linearly constrained nonconvex composite problems ⋮ Average curvature FISTA for nonconvex smooth composite optimization problems ⋮ First-order methods for convex optimization ⋮ Conditional gradient type methods for composite nonlinear and stochastic optimization ⋮ Inexact proximal stochastic second-order methods for nonconvex composite optimization ⋮ Recent Theoretical Advances in Non-Convex Optimization ⋮ An Average Curvature Accelerated Composite Gradient Method for Nonconvex Smooth Composite Optimization Problems ⋮ A unified convergence analysis of stochastic Bregman proximal gradient and extragradient methods ⋮ A FISTA-type accelerated gradient algorithm for solving smooth nonconvex composite optimization problems ⋮ Accelerated first-order methods for large-scale convex optimization: nearly optimal complexity under strong convexity ⋮ An adaptive high order method for finding third-order critical points of nonconvex optimization ⋮ Accelerated Stochastic Algorithms for Nonconvex Finite-Sum and Multiblock Optimization ⋮ A new restricted memory level bundle method for constrained convex nonsmooth optimization ⋮ Generalized Momentum-Based Methods: A Hamiltonian Perspective ⋮ Universal intermediate gradient method for convex problems with inexact oracle

Uses Software

• L-BFGS
• PPROJ

Cites Work

• Unnamed Item
• Unnamed Item
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• On the global convergence rate of the gradient descent method for functions with Hölder continuous gradients
• Gradient methods for minimizing composite functions
• First-order methods of smooth convex optimization with inexact oracle
• An optimal method for stochastic composite optimization
• Universal gradient methods for convex optimization problems
• Representations of quasi-Newton matrices and their use in limited memory methods
• Introductory lectures on convex optimization. A basic course.
• Non-Euclidean restricted memory level method for large-scale convex optimization
• New variants of bundle methods
• Fast bundle-level methods for unconstrained and ball-constrained convex optimization
• Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization
• Stochastic simulation: Algorithms and analysis
• Projection onto a Polyhedron that Exploits Sparsity
• Feature Article: Optimization for simulation: Theory vs. Practice
• On the Complexity of Steepest Descent, Newton's and Regularized Newton's Methods for Nonconvex Unconstrained Optimization Problems
• Updating Quasi-Newton Matrices with Limited Storage
• Numerical Optimization
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization