(Near) Optimal Parallelism Bound for Fully Asynchronous Coordinate Descent with Linear Speedup
share
When solving massive optimization problems in areas such as machine learning, it is a common practice to seek speedup via massive parallelism. However, especially in an asynchronous environment, there are limits on the possible parallelism. Accordingly, we seek tight bounds on the viable parallelism in asynchronous implementations of coordinate descent. We focus on asynchronous coordinate descent (ACD) algorithms on convex functions F:R^n →R of the form F(x) = f(x) + ∑_k=1^n Ψ_k(x_k), where f:R^n →R is a smooth convex function, and each Ψ_k:R→R is a univariate and possibly non-smooth convex function. Our approach is to quantify the shortfall in progress compared to the standard sequential stochastic gradient descent. This leads to a truly simple yet optimal analysis of the standard stochastic ACD in a partially asynchronous environment, which already generalizes and improves on the bounds in prior work. We also give a considerably more involved analysis for general asynchronous environments in which the only constraint is that each update can overlap with at most q others, where q is at most the number of processors times the ratio in the lengths of the longest and shortest updates. The main technical challenge is to demonstrate linear speedup in the latter environment. This stems from the subtle interplay of asynchrony and randomization. This improves Liu and Wright's (SIOPT'15) lower bound on the maximum degree of parallelism almost quadratically, and we show that our new bound is almost optimal.
READ FULL TEXT