Asynchronous Proximal Stochastic Gradient Algorithm for Composition Optimization Problems
نویسندگان
چکیده
منابع مشابه
An Efficient Conjugate Gradient Algorithm for Unconstrained Optimization Problems
In this paper, an efficient conjugate gradient method for unconstrained optimization is introduced. Parameters of the method are obtained by solving an optimization problem, and using a variant of the modified secant condition. The new conjugate gradient parameter benefits from function information as well as gradient information in each iteration. The proposed method has global convergence und...
متن کاملAsynchronous Parallel Stochastic Gradient for Nonconvex Optimization
Asynchronous parallel implementations of stochastic gradient (SG) have been broadly used in solving deep neural network and received many successes in practice recently. However, existing theories cannot explain their convergence and speedup properties, mainly due to the nonconvexity of most deep learning formulations and the asynchronous parallel mechanism. To fill the gaps in theory and provi...
متن کاملProximal gradient algorithm for group sparse optimization
In this paper, we propose a proximal gradient algorithm for solving a general nonconvex and nonsmooth optimization model of minimizing the summation of a C1,1 function and a grouped separable lsc function. This model includes the group sparse optimization via lp,q regularization as a special case. Our algorithmic scheme presents a unified framework for several well-known iterative thresholding ...
متن کاملAsynchronous Distributed Semi-Stochastic Gradient Optimization
With the recent proliferation of large-scale learning problems, there have been a lot of interest on distributed machine learning algorithms, particularly those that are based on stochastic gradient descent (SGD) and its variants. However, existing algorithms either suffer from slow convergence due to the inherent variance of stochastic gradients, or have a fast linear convergence rate but at t...
متن کاملAn Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization
We propose a distributed first-order augmented Lagrangian (DFAL) algorithm to minimize the sum of composite convex functions, where each term in the sum is a private cost function belonging to a node, and only nodes connected by an edge can directly communicate with each other. This optimization model abstracts a number of applications in distributed sensing and machine learning. We show that a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33011633