In this paper, we develop a stochastic-gradient learning algorithm for situations involving streaming data that arise from an underlying clustered structure. In such settings, the variance of gradient noise can be decomposed into the in-cluster variance σ in 2 plus the between-cluster variance σ bet 2 . We develop a cluster-based online variancereduced method (COVER) to eliminate σ bet 2 and improve the MSD performance of stochastic-gradient descent (SGD) to the order of O(σ in 2 ). We establish the convergence property of COVER and derive a tight closed-form mean-square deviation (MSD) performance expression. Our simulations illustrate the improved performance of COVER in terms of steady-state performance.
No takes yet. Share an insight, caveat, or question.
Yuan et al. (2019) studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: