Communication overhead is one of the key challenges that hinders the scalability of distributed optimization algorithms. In this paper, we study local distributed SGD, where data is partitioned among computation nodes, and the computation nodes perform local updates with periodically exchanging the model among the workers to perform averaging. While local SGD is empirically shown to provide promising results, a theoretical understanding of its performance remains open. In this paper, we strengthen convergence analysis for local SGD, and show that local SGD can be far less expensive and applied far more generally than current theory suggests. Specifically, we show that for loss functions that satisfy the Polyak-Kojasiewicz condition, $O((pT)^{1/3})$ rounds of communication suffice to achieve a linear speed up, that is, an error of $O(1/pT)$, where $T$ is the total number of model updates at each worker. This is in contrast with previous work which required higher number of communication rounds, as well as was limited to strongly convex loss functions, for a similar asymptotic performance. We also develop an adaptive synchronization scheme that provides a general condition for linear speed up.

Local SGD, a cornerstone algorithm in federated learning, is widely used in training deep neural networks and shown to have strong empirical performance. A theoretical understanding of such performance on nonconvex loss landscapes is currently lacking. Analysis of the global convergence of SGD is challenging, as the noise depends on the model parameters. Indeed, many works narrow their focus to GD and rely on injecting noise to enable convergence to the local or global optimum. When expanding the focus to local SGD, existing analyses in the nonconvex case can only guarantee finding stationary points or assume the neural network is overparameterized so as to guarantee convergence to the global minimum through neural tangent kernel analysis.

We analyze Local SGD (aka parallel or federated SGD) and Minibatch SGD in the heterogeneous distributed setting, where each machine has access to stochastic gradient estimates for a different, machine-specific, convex objective; the goal is to optimize w.r.t.~the average objective; and machines can only communicate intermittently. We argue that, (i) Minibatch SGD (even without acceleration) dominates all existing analysis of Local SGD in this setting, (ii) accelerated Minibatch SGD is optimal when the heterogeneity is high, and (iii) present the first upper bound for Local SGD that improves over Minibatch SGD in a non-homogeneous regime.

Communication overhead is one of the key challenges that hin ders the scalability of distributed optimization algorithms. In this paper, we s tudy local distributed SGD, where data is partitioned among computation nodes, and the computation nodes perform local updates with periodically exchanging t he model among the workers to perform averaging. While local SGD is empirically shown to provide promising results, a theoretical understanding of its performance remains open. We strengthen convergence analysis for local SGD, and show that local SGD can be far less expensive and applied far more generally t han current theory suggests.

We note that despite very recent observations on empirical superiority of adaptive synchronization (e.g., Surely, it would be interesting to see if our bound can be tightened. R1. log T communication rounds clarification: However, for local SGD with periodic averaging the proof techniques are more involved. We do not tune the learning rate.

In this paper we consider linearly constrained stochastic approximation problems with federated learning as a special case.

This method requires each worker to share their computed gradients with each other at every iteration. We will refer to this method as "synchronized parallel SGD."

Local SGD that improves over Minibatch SGD in a non-homogeneous regime.

Federated learning (FL) is now recognized as a key framework for communication-efficient collaborative learning. Most theoretical and empirical studies, however, rely on the assumption that clients have access to pre-collected data sets, with limited investigation into scenarios where clients continuously collect data. In many real-world applications, particularly when data is generated by physical or biological processes, client data streams are often modeled by non-stationary Markov processes. Unlike standard i.i.d. sampling, the performance of FL with Markovian data streams remains poorly understood due to the statistical dependencies between client samples over time. In this paper, we investigate whether FL can still support collaborative learning with Markovian data streams. Specifically, we analyze the performance of Minibatch SGD, Local SGD, and a variant of Local SGD with momentum. We answer affirmatively under standard assumptions and smooth non-convex client objectives: the sample complexity is proportional to the inverse of the number of clients with a communication complexity comparable to the i.i.d. scenario. However, the sample complexity for Markovian data streams remains higher than for i.i.d. sampling.