Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization (2018, methodology): “The SVRG analysis [13] requires the number of stochastic gradient updates to be scales as the condition number, so here we will use O(H √ nB/(LK)) communication rounds to perform the stochastic updates, since one chain within each communication round has length K.”
Cross-Iteration Coded Computing (2018, background): “A thematic direction of research motivated by our work is the idea of merging cross-iteration coded computing based and the ideas of [46]–[48] to reduce the storage cost of cross-iteration coded computing, but perhaps improve on the fidelity and convergence guarantees of [46]–[48].”
Communication-Efficient Distributed Statistical Inference (2016, background): “…loss function is constructed as the fusion center that is allowed to access to n data points, previous communication lower bounds obtained in Lee et al. (2017), Zhang and Lin (2015b), and Shamir, Srebro, and Zhang (2014) still apply, and imply the optimality of the CSL in terms of the…”