On the Convergence of Asynchronous Parallel Iteration with Arbitrary Delays
نویسندگان
چکیده
Recent years have witnessed the surge of asynchronous parallel (async-parallel) iterative algorithms due to problems involving very large-scale data and a large number of decision variables. Because of asynchrony, the iterates are computed with outdated information, and the age of the outdated information, which we call delay, is the number of times it has been updated since its creation. Almost all recent works prove convergence under the assumption of a finite maximum delay and set their stepsize parameters accordingly. However, the maximum delay is practically unknown. This paper presents convergence analysis of an async-parallel method from a probabilistic viewpoint, and it allows for arbitrarily large delays. An explicit formula of stepsize that guarantees convergence is given depending on delays’ statistics. With p+ 1 identical processors, we empirically measured that delays closely follow the Poisson distribution with parameter p, matching our theoretical model, and thus the stepsize can be set accordingly. Simulations on both convex and nonconvex optimization problems demonstrate the validness of our analysis and also show that the existing maximum-delay induced stepsize is too conservative, often slowing down the convergence of the algorithm.
منابع مشابه
Structure theorems for partially asynchronous iterations of a nonnegative matrix with random delays
We consider partially asynchronous parallel iteration of a fixed nonnegative matrix with stationary ergodic interprocessor communication delays. We study the iteration via a random graph describing the interprocessor influences. Our major result is an invariant description of the rates of convergence of arbitrary sequences of individual processor-time values. In the course of proving this resul...
متن کاملOn the Convergence of Asynchronous Parallel Iteration with Unbounded Delays
Recent years have witnessed the surge of asynchronous parallel (async-parallel) iterative algorithms due to problems involving very large-scale data and a large number of decision variables. Because of asynchrony, the iterates are computed with outdated information, and the age of the outdated information, which we call delay, is the number of times it has been updated since its creation. Almos...
متن کاملOn Unbounded Delays in Asynchronous Parallel Fixed-Point Algorithms
The need for scalable numerical solutions has motivated the development of asynchronous parallel algorithms, where a set of nodes run in parallel with little or no synchronization, thus computing with delayed information. This paper studies the convergence of the asynchronous parallel algorithm ARock under potentially unbounded delays. ARock is a general asynchronous algorithm that has many app...
متن کاملPerturbation-Iteration Algorithm for Solving Heat and Mass Transfer in the Unsteady Squeezing Flow between Parallel Plates
In this paper, heat and mass transfer in the unsteady squeezing flow between parallel plates is analyzed using a perturbation-iteration algorithm. The similarity transformation is used to transform the governing partial differential equations into ordinary differential equations, before being solved. The solutions of the velocity, temperature and concentration are derived and sketched to explai...
متن کاملAsynchronous Coordinate Descent under More Realistic Assumptions
Asynchronous-parallel algorithms have the potential to vastly speed up algorithms by eliminating costly synchronization. However, our understanding of these algorithms is limited because the current convergence of asynchronous (block) coordinate descent algorithms are based on somewhat unrealistic assumptions. In particular, the age of the shared optimization variables being used to update a bl...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1612.04425 شماره
صفحات -
تاریخ انتشار 2016