Suchergebnisse - Prox-linear algorithm

Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization von Zhang, Junyu, Xiao, Lin

“… We propose a class of stochastic variance-reduced prox-linear algorithms for solving such problems and bound their sample complexities for finding an ϵ …”
Volltext

Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems von Yang, Zhen-Ping, Zhao, Yong

“… The first algorithm is the prox-linear hybrid stochastic gradient algorithm, which may achieve sample complexities of O(ϵ2τ−5/2) and O(ϵτ−3/2 …”
Volltext

Low-Rank Matrix Recovery with Composite Optimization: Good Conditioning and Rapid Convergence von Charisopoulos, Vasileios, Chen, Yudong, Davis, Damek, Díaz, Mateo, Ding, Lijun, Drusvyatskiy, Dmitriy

“… Consequently, standard algorithms for nonsmooth optimization, such as subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the solution …”
Volltext

Robust and Scalable Power System State Estimation via Composite Optimization von Wang, Gang, Giannakis, Georgios B., Chen, Jie

“… This paper, develops two novel algorithms for efficient LAV estimation, which draw from recent advances in composite optimization …”
Volltext

A Barzilai–Borwein-Like Iterative Half Thresholding Algorithm for the L1/2 Regularized Problem von Wu, Lei, Sun, Zhe, Li, Dong-Hui

“… In this paper, we propose a Barzilai–Borwein-like iterative half thresholding algorithm for the L 1 / 2 regularized problem …”
Volltext

Stochastic Variance-Reduced Prox-Linear Algorithms for Nonconvex Composite Optimization von Zhang, Junyu, Lin, Xiao

“… We propose a class of stochastic variance-reduced prox-linear algorithms for solving such problems and bound their sample complexities for finding an \(\epsilon …”
Volltext

Hyperparameter tuning via trajectory predictions: stochastic prox-linear methods in matrix sensing von Lou, Mengqi, Verchand, Kabir Aladin, Pananjady, Ashwin

“… Motivated by the desire to understand stochastic algorithms for nonconvex optimization that are robust to their hyperparameter choices, we analyze a mini-batched prox-linear iterative algorithm …”
Volltext

REAL-TIME POWER SYSTEM STATE ESTIMATION VIA DEEP UNROLLED NEURAL NETWORKS von Zhang, Liang, Wang, Gang, Giannakis, Georgios B.

“… model-specific DNN is obtained by unrolling state-of-the-art physics-based prox-linear PSSE solvers …”
Volltext

A Globally Convergent Algorithm for Nonconvex Optimization Based on Block Coordinate Update von Xu, Yangyang, Yin, Wotao

“… However, most nonconvex optimization algorithms are only known to have local convergence or subsequence convergence properties …”
Volltext

Efficiency of minimizing compositions of convex functions and smooth maps von Drusvyatskiy, D., Paquette, C.

“… The basic algorithm we rely on is the prox-linear method, which in each iteration solves a regularized subproblem formed by linearizing the smooth map …”
Volltext

Hyperparameter tuning via trajectory predictions: Stochastic prox-linear methods in matrix sensing von Mengqi Lou, Kabir, Aladin Verchand, Pananjady, Ashwin

“… Motivated by the desire to understand stochastic algorithms for nonconvex optimization that are robust to their hyperparameter choices, we analyze a mini-batched prox-linear iterative algorithm …”
Volltext

Stochastic algorithms with geometric step decay converge linearly on sharp functions von Davis, Damek, Drusvyatskiy, Dmitriy, Charisopoulos, Vasileios

“… In this work, we ask whether geometric step decay similarly improves stochastic algorithms for the class of sharp weakly convex problems …”
Volltext

Accelerated-gradient-based generalized Levenberg–Marquardt method with oracle complexity bound and local quadratic convergence von Marumo, Naoki, Okuno, Takayuki, Takeda, Akiko

“… The generalized Levenberg–Marquardt (LM) method, also known as the prox-linear method, has been developed for such optimization problems …”
Volltext

The multiproximal linearization method for convex composite problems von Bolte, Jérôme, Chen, Zheng, Pauwels, Edouard

“… In the convex setting, we design an algorithm by linearizing each smooth component in accordance with its main curvature …”
Volltext

Large-Scale Distributed Sparse Class-Imbalance Learning von Maurya, Chandresh Kumar, Toshniwal, Durga

“… Each node runs a local copy of FISTA-like algorithm which is a distributed implementation of the prox-linear algorithm for cost-sensitive learning. We show the efficacy of the proposed approach on benchmark and real-world data sets and compare the performance with the state-of-the-art techniques in the literature …”
Volltext

Multi-Label Nonlinear Matrix Completion With Transductive Multi-Task Feature Selection for Joint MGMT and IDH1 Status Prediction of Patient With High-Grade Gliomas von Chen, Lei, Zhang, Han, Lu, Junfeng, Thung, Kimhan, Aibaidula, Abudumijiti, Liu, Luyan, Chen, Songcan, Jin, Lei, Wu, Jinsong, Wang, Qian, Zhou, Liangfu, Shen, Dinggang

“… The O 6 -methylguanine-DNA methyltransferase (MGMT) promoter methylation and isocitrate dehydrogenase 1 (IDH1) mutation in high-grade gliomas (HGG) have proven …”
Volltext

A Proximal Atomic Coordination Algorithm for Distributed Optimization von Romvary, Jordan J., Ferro, Giulio, Haider, Rabab, Annaswamy, Anuradha M.

“… ). PAC is based on the prox-linear approach and we prove that it achieves convergence in both objective values and distance to feasibility with rate o(1/<inline …”
Volltext

Continuous-time successive convexification for constrained trajectory optimization von Elango, Purnanand, Luo, Dayou, Kamath, Abhinav G., Uzun, Samet, Kim, Taewan, Açıkmeşe, Behçet

“… ; and (v) the prox-linear method, a sequential convex programming (SCP) algorithm for convex-composite minimization …”
Volltext

Dynamic reconfigurable intelligent surface deployment for physical layer security enhancement in mmWave systems von Tu, Qingqing, Dong, Zheng, Zou, Xianbing, Wei, Ning, Li, Ya, Xu, Fei

“… In next‐generation wireless communications, reconfigurable intelligent surface (RIS) has emerged as a cost‐effective technique for enhancing physical layer …”
Volltext

Classification of Directed Networks With Application to Neuroimaging Data von Chen, Li, Liu, Yuncheng, Lin, Lizhen, Zhang, Dongpei

“… Graph-based classification techniques applied to neuroimaging data have played a pivotal role in advancing our comprehension of brain functionalities. Existing …”
Volltext