Finite-Time Convergence Rates of Decentralized Stochastic Approximation with Applications in Multi-Agent and Multi-Task Learning
This provides a theoretical foundation for decentralized learning in multi-agent systems, addressing a key bottleneck in handling dependent data, though it is incremental as it extends existing analysis to Markovian settings.
The paper tackles the problem of decentralized stochastic approximation with Markovian data, which introduces bias and potential unboundedness in iterates, and shows that the convergence rate remains essentially the same as with independent samples, differing only by a log factor related to the mixing time.
We study a decentralized variant of stochastic approximation, a data-driven approach for finding the root of an operator under noisy measurements. A network of agents, each with its own operator and data observations, cooperatively find the fixed point of the aggregate operator over a decentralized communication graph. Our main contribution is to provide a finite-time analysis of this decentralized stochastic approximation method when the data observed at each agent are sampled from a Markov process; this lack of independence makes the iterates biased and (potentially) unbounded. Under fairly standard assumptions, we show that the convergence rate of the proposed method is essentially the same as if the samples were independent, differing only by a log factor that accounts for the mixing time of the Markov processes. The key idea in our analysis is to introduce a novel Razumikhin-Lyapunov function, motivated by the one used in analyzing the stability of delayed ordinary differential equations. We also discuss applications of the proposed method on a number of interesting learning problems in multi-agent systems.