Distributed Momentum Methods Under Biased Gradient Estimations

arXiv:2403.00853v1 Announce Type: new
Abstract: Distributed stochastic gradient methods are gaining prominence in solving large-scale machine learning problems that involve data distributed across multiple nodes. However, obtaining unbiased stochastic gradients, which have been the focus of most theoretical research, is challenging in many distributed machine learning applications. The gradient estimations easily become biased, for example, when gradients are compressed or clipped, when data is shuffled, and in meta-learning and reinforcement learning. In this work, we establish non-asymptotic convergence bounds on …

abstract applications arxiv become cs.lg data distributed estimations focus gradient machine machine learning machine learning applications multiple nodes research scale stochastic type unbiased