An Accelerated Composite Gradient Method for Large-Scale Composite Objective Problems
From MaRDI portal
Abstract: We introduce a framework, which we denote as the augmented estimate sequence, for deriving fast algorithms with provable convergence guarantees. We use this framework to construct a new first-order scheme, the Accelerated Composite Gradient Method (ACGM), for large-scale problems with composite objective structure. ACGM surpasses the state-of-the-art methods for this problem class in terms of provable convergence rate, both in the strongly and non-strongly convex cases, and is endowed with an efficient step size search procedure. We support the effectiveness of our new method with simulation results.
Cited in
(18)- Accelerated inexact composite gradient methods for nonconvex spectral optimization problems
- Accelerated randomized mirror descent algorithms for composite non-strongly convex optimization
- Exact gradient methods with memory
- Backtracking strategies for accelerated descent methods with smooth composite objectives
- Scaled, inexact, and adaptive generalized FISTA for strongly convex optimization
- Iteration Complexity of an Inner Accelerated Inexact Proximal Augmented Lagrangian Method Based on the Classical Lagrangian Function
- An accelerated proximal gradient method for multiobjective optimization
- An adaptive superfast inexact proximal augmented Lagrangian method for smooth nonconvex composite optimization problems
- Linearly-convergent FISTA variant for composite optimization with duality
- A proximal augmented Lagrangian method for linearly constrained nonconvex composite optimization problems
- Complexity-optimal and parameter-free first-order methods for finding stationary points of composite optimization problems
- A C-FISTA-type Krasnosel'skiĭ-Mann iteration with applications to TV-based denoising problem and image in-painting
- Inexact FISTA-like methods with adaptive backtracking
- An optimal lower bound for smooth convex functions
- Efficient parameter-free restarted accelerated gradient methods for convex and strongly convex optimization
- C-FISTA type projection algorithm for quasi-variational inequalities
- Nesterov's acceleration at the limit: first-order schemes
- A C-FISTA-type proximal point algorithm for strongly quasiconvex pseudomonotone equilibrium problems
This page was built for publication: An Accelerated Composite Gradient Method for Large-Scale Composite Objective Problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4628200)
