Distributed Algorithms for Composite Optimization: Unified Framework and Convergence Analysis
نویسندگان
چکیده
We study distributed composite optimization over networks: agents minimize a sum of smooth (strongly) convex functions-the agents' sum-utility-plus nonsmooth (extended-valued) one. propose general unified algorithmic framework for such class problems and provide convergence analysis leveraging the theory operator splitting. Distinguishing features our scheme are: (i) When each agent's functions is strongly convex, algorithm converges at linear rate, whose dependence on network topology decoupled; (ii) objective function (but not convex), similar decoupling as in established coefficient proved sublinear rate. This also reveals role heterogeneity (iii) The can adjust ratio between number communications computations to achieve rate (in terms computations) independent connectivity; (iv) A by-product tuning recommendation several existing (non-accelerated) algorithms yielding provably faster (worst-case) under consideration.
منابع مشابه
Convergence Analysis of Optimization Algorithms
The regret bound of an optimization algorithms is one of the basic criteria for evaluating the performance of the given algorithm. By inspecting the differences between the regret bounds of traditional algorithms and adaptive one, we provide a guide for choosing an optimizer with respect to the given data set and the loss function. For analysis, we assume that the loss function is convex and it...
متن کاملA Framework for Adapting Population-Based and Heuristic Algorithms for Dynamic Optimization Problems
In this paper, a general framework was presented to boost heuristic optimization algorithms based on swarm intelligence from static to dynamic environments. Regarding the problems of dynamic optimization as opposed to static environments, evaluation function or constraints change in the time and hence place of optimization. The subject matter of the framework is based on the variability of the ...
متن کاملAnalysis of Algorithms for Distributed Optimization
Gradient descent (GD) and coordinate descent (CD) are two competing families of optimization algorithms used to solve numerous machine learning tasks. The proliferation of large, web-scale datasets has led researchers to investigate minibatch variants of these algorithms in parallel and distributed settings. However, there is a lack of consensus in the community about the relative merits of the...
متن کاملMultiuser Optimization: Distributed Algorithms and Error Analysis
Traditionally, a multiuser problem is a constrained optimization problem characterized by a set of users, an objective given by a sum of user-specific utility functions, and a collection of linear constraints that couple the user decisions. The users do not share the information about their utilities, but do communicate values of their decision variables. The multiuser problem is to maximize th...
متن کاملA Unified Monitoring Framework for Distributed Environment
Distributed computing is a field of computer science that studies distributed systems. With the increasing computing capacity of computers it is widely used to solve large problems. Monitoring system is one of the key components in distributed computing. Although there have been varieties of monitoring systems developed by different organizations, it is still a great challenge to monitor a hete...
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: 2021
ISSN: ['1053-587X', '1941-0476']
DOI: https://doi.org/10.1109/tsp.2021.3086579