S-ADDOPT: Decentralized stochastic first-order optimization over directed graphs

by   Muhammad I. Qureshi, et al.

In this report, we study decentralized stochastic optimization to minimize a sum of smooth and strongly convex cost functions when the functions are distributed over a directed network of nodes. In contrast to the existing work, we use gradient tracking to improve certain aspects of the resulting algorithm. In particular, we propose the S-ADDOPT algorithm that assumes a stochastic first-order oracle at each node and show that for a constant step-size α, each node converges linearly inside an error ball around the optimal solution, the size of which is controlled by α. For decaying step-sizes O(1/k), we show that S-ADDOPT reaches the exact solution sublinearly at O(1/k) and its convergence is asymptotically network-independent. Thus the asymptotic behavior of S-ADDOPT is comparable to the centralized stochastic gradient descent. Numerical experiments over both strongly convex and non-convex problems illustrate the convergence behavior and the performance comparison of the proposed algorithm.



There are no comments yet.


page 1

page 2

page 3

page 4


Push-SAGA: A decentralized stochastic algorithm with variance reduction over directed graphs

In this paper, we propose Push-SAGA, a decentralized stochastic first-or...

Distributed stochastic optimization with gradient tracking over strongly-connected networks

In this paper, we study distributed stochastic optimization to minimize ...

A hybrid variance-reduced method for decentralized stochastic non-convex optimization

This paper considers decentralized stochastic optimization over a networ...

Swarming for Faster Convergence in Stochastic Optimization

We study a distributed framework for stochastic optimization which is in...

Linearly Convergent Algorithm with Variance Reduction for Distributed Stochastic Optimization

This paper considers a distributed stochastic strongly convex optimizati...

Linear Convergence of Adaptive Stochastic Gradient Descent

We prove that the norm version of the adaptive stochastic gradient metho...

Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD

We consider decentralized stochastic optimization problems where a netwo...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.