Global complexity analysis of inexact successive quadratic approximation methods for regularized optimization under mild assumptions
From MaRDI portal
Publication:2200083
Abstract: Successive quadratic approximations (SQA) are numerically efficient for minimizing the sum of a smooth function and a convex function. The iteration complexity of inexact SQA methods has been analyzed recently. In this paper, we present an algorithmic framework of inexact SQA methods with four types of line searches, and analyze its global complexity under milder assumptions. First, we show its well-definedness and some decreasing properties. Second, under the quadratic growth condition and a uniform positive lower bound condition on stepsizes, we show that the function value sequence and the iterate sequence are linearly convergent. Moreover, we obtain a o(1/k) complexity without the quadratic growth condition, improving existing O(1/k) complexity results. At last, we show that a local gradient-Lipschitz-continuity condition could guarantee a uniform positive lower bound for the stepsizes.
Recommendations
- Inexact successive quadratic approximation for regularized optimization
- Accelerating inexact successive quadratic approximation for regularized optimization through manifold identification
- An inexact successive quadratic approximation method for L-1 regularized optimization
- A family of inexact SQA methods for non-smooth convex minimization with provable convergence guarantees based on the Luo-Tseng error bound property
- Global and superlinear convergence of inexact sequential quadratically constrained quadratic programming method for convex programming
Cites work
- A coordinate gradient descent method for nonsmooth separable minimization
- A descent lemma beyond Lipschitz gradient continuity: first-order methods revisited and applications
- A family of inexact SQA methods for non-smooth convex minimization with provable convergence guarantees based on the Luo-Tseng error bound property
- A Modified Forward-Backward Splitting Method for Maximal Monotone Mappings
- A preconditioning proximal Newton method for nondifferentiable convex optimization
- An improved GLMNET for L1-regularized logistic regression
- An inexact successive quadratic approximation method for L-1 regularized optimization
- Convergence analysis of a proximal newton method1
- Convergence of convex sets and of solutions of variational inequalities
- Convex analysis and monotone operator theory in Hilbert spaces
- Exact worst-case convergence rates of the proximal gradient method for composite convex minimization
- First-order methods in optimization
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Inexact successive quadratic approximation for regularized optimization
- Iterative methods for fixed point problems in Hilbert spaces
- Linear convergence of first order methods for non-strongly convex optimization
- New analysis of linear convergence of gradient-type methods via unifying error bound conditions
- On equiwellset minimum problems
- On the convergence of the forward-backward splitting method with linesearches
- On Weak and Strong Convergence of the Projected Gradient Method for Convex Optimization in Real Hilbert Spaces
- Practical inexact proximal quasi-Newton method with global complexity analysis
- Proximal Newton-type methods for minimizing composite functions
- Signal Recovery by Proximal Forward-Backward Splitting
- The Variable Metric Forward-Backward Splitting Algorithm Under Mild Differentiability Assumptions
Cited in
(6)- A family of inexact SQA methods for non-smooth convex minimization with provable convergence guarantees based on the Luo-Tseng error bound property
- Inexact variable metric stochastic block-coordinate descent for regularized optimization
- An inexact successive quadratic approximation method for a class of difference-of-convex optimization problems
- Inexact successive quadratic approximation for regularized optimization
- Accelerating inexact successive quadratic approximation for regularized optimization through manifold identification
- An inexact variable metric variant of incremental aggregated Forward-Backward method for the large-scale composite optimization problem
This page was built for publication: Global complexity analysis of inexact successive quadratic approximation methods for regularized optimization under mild assumptions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2200083)
