Asynchronous Incremental Stochastic Dual Descent Algorithm for Network Resource Allocation
نویسندگان
چکیده
منابع مشابه
Learn-and-Adapt Stochastic Dual Gradients for Network Resource Allocation
Network resource allocation shows revived popularity in the era of data deluge and information explosion. Existing stochastic optimization approaches fall short in attaining a desirable cost-delay tradeoff. Recognizing the central role of Lagrange multipliers in network resource allocation, a novel learn-andadapt stochastic dual gradient (LA-SDG) method is developed in this paper to learn the s...
متن کاملAn Asynchronous Parallel Stochastic Coordinate Descent Algorithm
We describe an asynchronous parallel stochastic coordinate descent algorithm for minimizing smooth unconstrained or separably constrained functions. The method achieves a linear convergence rate on functions that satisfy an essential strong convexity property and a sublinear rate (1/K) on general convex functions. Near-linear speedup on a multicore system can be expected if the number of proces...
متن کاملPASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent
Stochastic Dual Coordinate Descent (DCD) is one of the most efficient ways to solve the family of `2-regularized empirical risk minimization problems, including linear SVM, logistic regression, and many others. The vanilla implementation of DCD is quite slow; however, by maintaining primal variables while updating dual variables, the time complexity of DCD can be significantly reduced. Such a s...
متن کاملAsynchronous Accelerated Stochastic Gradient Descent
Stochastic gradient descent (SGD) is a widely used optimization algorithm in machine learning. In order to accelerate the convergence of SGD, a few advanced techniques have been developed in recent years, including variance reduction, stochastic coordinate sampling, and Nesterov’s acceleration method. Furthermore, in order to improve the training speed and/or leverage larger-scale training data...
متن کاملAn Algorithm for Resource Allocation through the Classification of DMUs
Data envelopment analysis (DEA) is a non-parametric method for assessing relative efficiency of decision-making units (DMUs). Every single decision-maker with the use of inputs produces outputs. These decision-making units will be defined by the production possibility set. Resource allocation to DMUs is one of the concerns of managers since managers can employ the results of this process to 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: IEEE Transactions on Signal Processing
سال: 2018
ISSN: 1053-587X,1941-0476
DOI: 10.1109/tsp.2018.2807423