Výsledky vyhledávání - alternating gradient descent and minimization algorithm

Provable Active Multi-Task Representation Learning Autor Lin, Jiabin, Moothedath, Shana, Le, Tuan Anh

“… By leveraging the techniques from active learning, we propose an adaptive sampling-based alternating projected gradient descent (GD…”
Získat plný text

Robust Matrix Completion via Maximum Correntropy Criterion and Half-Quadratic Optimization Autor He, Yicong, Wang, Fei, Li, Yingsong, Qin, Jing, Chen, Badong

“… Two efficient algorithms are then derived: an alternating minimization-based algorithm and an alternating gradient descent-based algorithm…”
Získat plný text

Gradient-based optimisation of the conditional-value-at-risk using the multi-level Monte Carlo method Autor Ganesh, Sundar, Nobile, Fabio

“… We then propose combining the MLMC framework with an alternating inexact minimisation-gradient descent algorithm, for which we prove Q-linear convergence in the optimisation…”
Získat plný text

Decentralized Nonconvex Low-rank Matrix Recovery Autor Gao, Junzhuo, Lian, Heng

“… Matrix factorization is a computationally efficient nonconvex approach for low-rank matrix recovery, utilizing an alternating minimization or a gradient descent algorithm, and its theoretical…”
Získat plný text

Efficient and Fast Joint Sparse Constrained Canonical Correlation Analysis for Fault Detection Autor Xiu, Xianchao, Pan, Lili, Yang, Ying, Liu, Wanquan

“… We then develop an efficient alternating minimization algorithm using the improved iterative hard thresholding and manifold constrained gradient descent method…”
Získat plný text

Fast Alternating Direction Optimization Methods Autor Goldstein, Tom, O'Donoghue, Brendan, Setzer, Simon, Baraniuk, Richard

“…: the alternating direction method of multipliers (ADMM) and the alternating minimization algorithm (AMA…”
Získat plný text

Efficient Federated Low Rank Matrix Recovery via Alternating GD and Minimization: A Simple Proof Autor Vaswani, Namrata

“…This note provides a significantly simpler and shorter proof of our sample complexity guarantee for solving the low rank column-wise sensing problem using the Alternating Gradient Descent (GD) and Minimization (AltGDmin) algorithm…”
Získat plný text

Fast and Sample-Efficient Relevance-Based Multi-Task Representation Learning Autor Lin, Jiabin, Moothedath, Shana

“… We present a novel learning algorithm based on an alternating projected gradient descent (GD) and minimization estimator…”
Získat plný text

Poisson Noise Removal Scheme Based on Fourth-Order PDE by Alternating Minimization Algorithm Autor Zhou, Weifeng, Li, Qingguo

“…) filter for removing Poisson noise. In consideration of the slow convergence property of the classical gradient descent method, we adopt the alternating minimization algorithm for realizing this scheme…”
Získat plný text

Low rank matrix completion by alternating steepest descent methods Autor Tanner, Jared, Wei, Ke

“… In this paper, we introduce an alternating steepest descent algorithm (ASD) and a scaled variant, ScaledASD, for the fixed-rank matrix completion problem…”
Získat plný text

Symmetric tensor decomposition by alternating gradient descent Autor Liu, Haixia

“… We use alternating gradient descent algorithm to solve. Although we focus on symmetric tensors in this article…”
Získat plný text

Sparse Index Tracking With K-Sparsity or ϵ-Deviation Constraint via ℓ0-Norm Minimization Autor Li, Xiao Peng, Shi, Zhang-Lei, Leung, Chi-Sing, So, Hing Cheung

“… This article formulates sparse index tracking as two constrained optimization problems and then proposes two algorithms, namely, nonnegative orthogonal matching pursuit with projected gradient descent (NNOMP-PGD…”
Získat plný text

Fast Rank-One Alternating Minimization Algorithm for Phase Retrieval Autor Cai, Jian-Feng, Liu, Haixia, Wang, Yang

“… An alternating gradient descent algorithm is proposed, and its convergence for any initialization is provided…”
Získat plný text

Robust Low-Rank Tensor Minimization via a New Tensor Spectral k -Support Norm Autor Lou, Jian, Cheung, Yiu-Ming

“…Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank…”
Získat plný text

Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward–backward splitting, and regularized Gauss–Seidel methods Autor Attouch, Hedy, Bolte, Jérôme, Svaiter, Benar Fux

“…In view of the minimization of a nonsmooth nonconvex function f , we prove an abstract convergence result for descent methods satisfying a sufficient-decrease assumption, and allowing a relative error tolerance…”
Získat plný text

Millimeter-Wave Beamformed Full-Dimensional MIMO Channel Estimation Based on Atomic Norm Minimization Autor Tsai, Yingming, Zheng, Le, Wang, Xiaodong

“…) and non-uniform planar arrays (NUPA). Unlike existing algorithms, such as compressive sensing (CS…”
Získat plný text

Fast Low Rank Column-Wise Compressive Sensing for Accelerated Dynamic MRI Autor Babu, Silpa, Lingala, Sajan Goud, Vaswani, Namrata

“…This work develops a novel set of algorithms, alternating Gradient Descent (GD) and minimization for MRI…”
Získat plný text

Fourier Phase Retrieval with Arbitrary Reference Signal Autor Arab, Fahimeh, Asif, M. Salman

“… In this paper, we present a Fourier phase retrieval algorithm in the presence of a known (reference) signal at arbitrary location in the scene…”
Získat plný text

Removal of Mainbeam Jamming Signals With Dual-Compensation-Phase Coding Radar Autor Zhang, Xiang, Lan, Lan, Zhu, Shengqi, Liao, Guisheng, Li, Ximin

“…This article investigates the removal of mainbeam jamming signals using a dual-compensation-phase coding (DC-PC) radar. At the transmitter, the waveforms are…”
Získat plný text

Phase retrieval based on a total‐variation‐regularized Poisson model for X‐ray ptychographic imaging of low‐contrast objects Autor Yatabe, Kohei, Takayama, Yuki

“…‐retrieval algorithm, AMPAM, based on the Poisson model and total variation (TV) is proposed. It applies alternating minimization using primal…”
Získat plný text