Distributed Stochastic Gradient Tracking Methods II: With Stepsizes θ/(m+k), DSGT's Mean-Square Error Is at Most 2θ²σ²/(n(θμ−1)(m+k)) Plus Higher-Order TermsResearch Paper
Many learning and estimation problems are solved by a group of computing agents that each hold part of the data and can talk only to their neighbours in a communication network. Each agent has a private cost , and the group wants a minimizer of the average without a central coordinator. In machine learning the agents usually cannot…