A stochastic successive minimization method for nonsmooth nonconvex optimization with applications to transceiver design in wireless communication networks

DOI10.1007/S10107-016-1021-7zbMATH Open1357.90101arXiv1307.4457OpenAlexW1491719355MaRDI QIDQ301668FDOQ301668

Authors: Meisam Razaviyayn, Maziar Sanjabi, Zhi-Quan Luo 

Publication date: 1 July 2016

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Abstract: Consider the problem of minimizing the expected value of a cost function parameterized by a random variable. The classical sample average approximation (SAA) method for solving this problem requires minimization of an ensemble average of the objective at each step, which can be expensive. In this paper, we propose a stochastic successive upper-bound minimization method (SSUM) which minimizes an approximate ensemble average at each iteration. To ensure convergence and to facilitate computation, we require the approximate ensemble average to be a locally tight upper-bound of the expected cost function and be easily optimized. The main contributions of this work include the development and analysis of the SSUM method as well as its applications in linear transceiver design for wireless communication networks and online dictionary learning. Moreover, using the SSUM framework, we extend the classical stochastic (sub-)gradient (SG) method to the case of minimizing a nonsmooth nonconvex objective function and establish its convergence.

Full work available at URL: https://arxiv.org/abs/1307.4457

Recommendations

• Stochastic generalized gradient method for nonconvex nonsmooth stochastic optimization
• Feasible methods for nonconvex nonsmooth problems with applications in green communications
• A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization
• Solution of nonconvex nonsmooth stochastic optimization problems
• Smooth sample average approximation of stationary points in nonsmooth stochastic optimization and applications

zbMATH Keywords

sample average approximationinner approximationstochastic beamformer designstochastic successive upper-bound minimization

Mathematics Subject Classification ID

Stochastic programming (90C15) Communication networks in operations research (90B18)

Cites Work

• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Title not available (Why is that?)
• Asymptotic Statistics
• The Concave-Convex Procedure
• A unified convergence analysis of block successive minimization methods for nonsmooth optimization
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Stochastic Approximation Method
• Primal-dual subgradient methods for convex problems
• Robust Stochastic Approximation Approach to Stochastic Programming
• Title not available (Why is that?)
• On stochastic gradient and subgradient methods with adaptive steplength sequences
• Title not available (Why is that?)
• Title not available (Why is that?)
• Online learning for matrix factorization and sparse coding
• Dual averaging methods for regularized stochastic learning and online optimization
• Title not available (Why is that?)
• Lectures on Stochastic Programming
• An Incremental Gradient(-Projection) Method with Momentum Term and Adaptive Stepsize Rule
• Gradient Convergence in Gradient methods with Errors
• Title not available (Why is that?)
• Symmetric Measures on Cartesian Products
• Decomposition by Partial Linearization: Parallel Optimization of Multi-Agent Systems
• Title not available (Why is that?)
• General bounds and finite-time improvement for the Kiefer-Wolfowitz stochastic approximation algorithm
• Distributed asynchronous deterministic and stochastic gradient optimization algorithms
• Regularized Iterative Stochastic Approximation Methods for Stochastic Variational Inequality Problems
• Stochastic Estimation of the Maximum of a Regression Function
• Stochastic generalized gradient method for nonconvex nonsmooth stochastic optimization
• Sample-path optimization of convex stochastic performance functions
• Convergence theory for nonconvex stochastic programming with an application to mixed logit
• Weighted sum-rate maximization in wireless networks: a review
• Mutual Information and Minimum Mean-Square Error in Gaussian Channels
• stochastic quasigradient methods and their application to system optimization^†
• Distributed asynchronous computation of fixed points
• A New Class of Incremental Gradient Methods for Least Squares Problems
• Robust Linear Precoder Design for Multi-Cell Downlink Transmission
• An Iteratively Weighted MMSE Approach to Distributed Sum-Utility Maximization for a MIMO Interfering Broadcast Channel
• Coordinated Beamforming for Multiuser MISO Interference Channel Under Rate Outage Constraints
• Joint User Grouping and Transceiver Design in a MIMO Interfering Broadcast Channel
• Title not available (Why is that?)
• Analysis of Sample-Path Optimization
• Title not available (Why is that?)
• Linear Transceiver Design for Interference Alignment: Complexity and Computation
• Optimal Resource Allocation for MIMO Ad Hoc Cognitive Radio Networks
• Quasi-Martingales
• New Classes of Synchronous Codes
• On a Stochastic Approximation Method
• A Stackelberg game approach to distributed spectrum management
• Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming

Cited In (8)

• On the pervasiveness of difference-convexity in optimization and statistics
• Incremental majorization-minimization optimization with application to large-scale machine learning
• DC programming and DCA: thirty years of developments
• A generalized proximal linearized algorithm for DC functions with application to the optimal size of the firm problem
• Global implicit function theorems and the online expectation–maximisation algorithm
• Stochastic difference-of-convex-functions algorithms for nonconvex programming
• Feasible methods for nonconvex nonsmooth problems with applications in green communications
• Stream-suitable optimization algorithms for some soft-margin support vector machine variants

This page was built for publication: A stochastic successive minimization method for nonsmooth nonconvex optimization with applications to transceiver design in wireless communication networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q301668)