Incremental Subgradients for Constrained Convex Optimization: A Unified Framework and New Methods

Authors:
Elias Salomão Helou Neto;Álvaro Rodolfo De Pierro
Affiliations:
e950514@ime.unicamp.br and alvaro@ime.unicamp.br;-
Venue:
SIAM Journal on Optimization
Year:
2009

Citing 22
Cited 0

Minimization methods for non-differentiable functions

Minimization methods for non-differentiable functions
A relaxed version of Bregman's method for convex programming

Journal of Optimization Theory and Applications
A parallel subgradient projections method for the convex feasibility problem

Journal of Computational and Applied Mathematics
On the convergence of the LMS algorithm with adaptive learning rate for linear feedforward networks

Neural Computation
Convergence of some algorithms for convex minimization

Mathematical Programming: Series A and B - Special issue: Festschrift in Honor of Philip Wolfe part II: studies in nonlinear programming
On Projection Algorithms for Solving Convex Feasibility Problems

SIAM Review
Error stability properties of generalized gradient-type algorithms

Journal of Optimization Theory and Applications
Incremental Gradient Algorithms with Stepsizes Bounded Away from Zero

Computational Optimization and Applications
Strong Convergence of Block-Iterative Outer Approximation Methods for Convex Optimization

SIAM Journal on Control and Optimization
Mathematical methods in image reconstruction

Mathematical methods in image reconstruction
An Incremental Gradient(-Projection) Method with Momentum Term and Adaptive Stepsize Rule

SIAM Journal on Optimization
A New Class of Incremental Gradient Methods for Least Squares Problems

SIAM Journal on Optimization
Gradient Convergence in Gradient methods with Errors

SIAM Journal on Optimization
Incremental Subgradient Methods for Nondifferentiable Optimization

SIAM Journal on Optimization
Convergence of Approximate and Incremental Subgradient Methods for Convex Optimization

SIAM Journal on Optimization
A level-set subgradient projection algorithm for non-differentiable signal restoration with multiple constraints

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 01
A Convergent Incremental Gradient Method with a Constant Step Size

SIAM Journal on Optimization
Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

IEEE Transactions on Information Theory
Compressed sensing

IEEE Transactions on Information Theory
Convex set theoretic image recovery by extrapolated iterations of parallel subgradient projections

IEEE Transactions on Image Processing
An adaptive level set method for nondifferentiable constrained image recovery

IEEE Transactions on Image Processing
Image restoration subject to a total variation constraint

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a unifying framework for nonsmooth convex minimization bringing together $\epsilon$-subgradient algorithms and methods for the convex feasibility problem. This development is a natural step for $\epsilon$-subgradient methods in the direction of constrained optimization since the Euclidean projection frequently required in such methods is replaced by an approximate projection, which is often easier to compute. The developments are applied to incremental subgradient methods, resulting in new algorithms suitable to large-scale optimization problems, such as those arising in tomographic imaging.