Výsledky vyhľadávania - Smoothing composite proximal gradient algorithm

Smoothing composite proximal gradient algorithm for sparse group Lasso problems with nonsmooth loss functions Autor Shen, Huiling, Peng, Dingtao, Zhang, Xian

“… Then, based on the smooth approximation of the loss function, a smoothing composite proximal gradient (SCPG…”
Získať plný text

Smoothing randomized block-coordinate proximal gradient algorithms for nonsmooth nonconvex composite optimization Autor Li, Xue, Bian, Wei

“…In this paper, we propose a smoothing randomized block-coordinate proximal gradient (S-RBCPG…”
Získať plný text

Proximal variable smoothing method for three-composite nonconvex nonsmooth minimization with a linear operator Autor Liu, Yuncheng, Xia, Fuquan

“… Based on the variable smoothing method, as well as first-order methods with suitable majorization techniques, we propose a proximal variable smoothing gradient (ProxVSG…”
Získať plný text

Zeroth-order Proximal Clipped Gradient Method with Shifts for Distributed Stochastic Composite Optimization Problems with Infinite Variance Autor Yang, Zhen-Ping, Chen, Pin-Bo, Zhao, Yong, Chen, Lin

“…-)gradient information may be unavailable. We present a mini-batch zeroth-order proximal clipped gradient algorithm with shifts, which utilizes the well-known Gaussian smoothing technique to yield unbiased zeroth-order gradient estimators…”
Získať plný text

Extrapolated Smoothing Descent Algorithm for Constrained Nonconvex and Nonsmooth Composite Problems Autor Chen, Yunmei, Liu, Hongcheng, Wang, Weina

“… Their algorithm adopts the proximal gradient algorithm with extrapolation and a safe-guarding policy to minimize the smoothed objective function for better practical and theoretical performance…”
Získať plný text

Adaptive smoothing algorithms for nonsmooth composite convex minimization Autor Tran-Dinh, Quoc

“…” nonsmooth composite convex optimization problems. Our method combines both Nesterov’s accelerated proximal gradient scheme and a new homotopy strategy for smoothness parameter…”
Získať plný text

A Proximal Variable Smoothing for Nonsmooth Minimization Involving Weakly Convex Composite with MIMO Application Autor Kume, Keita, Yamada, Isao

“…We propose a proximal variable smoothing algorithm for nonsmooth optimization problem with sum of three functions involving weakly convex composite function…”
Získať plný text

Zeroth-order Proximal Clipped Gradient Method with Shifts for Distributed Stochastic Composite Optimization Problems with Infinite Variance: Zeroth-order Proximal Clipped Gradient Method with Autor Yang, Zhen-Ping, Chen, Pin-Bo, Zhao, Yong, Chen, Lin

“…-)gradient information may be unavailable. We present a mini-batch zeroth-order proximal clipped gradient algorithm with shifts, which utilizes the well-known Gaussian smoothing technique to yield unbiased zeroth-order gradient estimators…”
Získať plný text

A Stochastic Nesterov’s Smoothing Accelerated Method for General Nonsmooth Constrained Stochastic Composite Convex Optimization Autor Wang, Ruyu, Zhang, Chao, Wang, Lichun, Shao, Yuanhai

“…We propose a novel stochastic Nesterov’s smoothing accelerated method for general nonsmooth, constrained, stochastic composite convex optimization, the nonsmooth component of which may be not easy to compute its proximal operator…”
Získať plný text

Distributed Stochastic Frank-Wolfe for Constrained Composite Minimization Autor Hou, Jie, Zeng, Xianlin, Cui, Shisheng, Wang, Gang, Sun, Jian

“… However, existing distributed algorithms for composite minimization are designed exclusively for the unconstrained setting…”
Získať plný text

An accelerated non-Euclidean hybrid proximal extragradient-type algorithm for convex-concave saddle-point problems Autor Kolossoski, O., Monteiro, R.D.C.

“… The algorithm is a special instance of a non-Euclidean hybrid proximal extragradient framework introduced by Svaiter and Solodov…”
Získať plný text

An Inexact Interior-Point Lagrangian Decomposition Algorithm with Inexact Oracles Autor Liu, Deyi, Tran-Dinh, Quoc

“…We combine the Lagrangian dual decomposition, barrier smoothing, path-following, and proximal Newton techniques to develop a new inexact interior-point Lagrangian decomposition method to solve a broad…”
Získať plný text

A Proximal Variable Smoothing for Nonsmooth Minimization Involving Weakly Convex Composite with MIMO Application Autor Kume, Keita, Yamada, Isao

“…We propose a proximal variable smoothing algorithm for nonsmooth optimization problem with sum of three functions involving weakly convex composite function…”
Získať plný text

General Convergence Analysis of Stochastic First-Order Methods for Composite Optimization Autor Necoara, Ion

“… Based on the flexibility offered by our optimization model, we consider several variants of stochastic first-order methods, such as the stochastic proximal gradient and the stochastic proximal point algorithms…”
Získať plný text

A Decentralized Proximal Gradient Tracking Algorithm for Composite Optimization on Riemannian Manifolds Autor Wang, Lei, Le, Bao, Liu, Xin

“…})\). This paper proposes a proximal gradient type algorithm that fully exploits the composite structure…”
Získať plný text

Composite convex optimization with global and local inexact oracles Autor Sun, Tianxiao, Necoara, Ion, Tran-Dinh, Quoc

“… Such inexact oracles naturally arise in many situations, including primal–dual frameworks, barrier smoothing, and inexact evaluations of gradients and Hessians…”
Získať plný text

Adaptive Smoothing Algorithms for Nonsmooth Composite Convex Minimization Autor Tran-Dinh, Quoc

“…} for solving "fully" nonsmooth composite convex optimization problems. Our method combines both Nesterov's accelerated proximal gradient scheme and a new homotopy strategy for smoothness parameter…”
Získať plný text

A Zeroth-order Proximal Stochastic Gradient Method for Weakly Convex Stochastic Optimization Autor Pougkakiotis, Spyridon, Kalogerias, Dionysios S

“… The proposed algorithm utilizes the well-known Gaussian smoothing technique, which yields unbiased zeroth-order gradient estimators of a related partially smooth surrogate problem…”
Získať plný text

Hybrid Conditional Gradient - Smoothing Algorithms with Applications to Sparse and Low Rank Regularization Autor Argyriou, Andreas, Signoretto, Marco, Suykens, Johan

“…We study a hybrid conditional gradient - smoothing algorithm (HCGS) for solving composite convex optimization problems which contain several terms over a bounded set…”
Získať plný text

Efficient and Provable Algorithms for Convex Optimization Problems Beyond Lipschitz Continuous Gradients Autor Liu, Deyi

“…This thesis aims at developing efficient algorithms for solving complex and constrained convex optimization problems with provable convergence guarantees…”
Získať plný text