L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework

29 citations recorded by the source corpus.

Reference EPFL-REPORT-229241 URL: http://arxiv.org/abs/1512.04011 Record created on 2017-06-21, modified on 2017-07-12

How researchers see this paper

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

CoCoA: A General Framework for Communication-Efficient Distributed Optimization (2016, background): “Portions of this newer work appear in SF’s Master’s Thesis (Forte, 2015) and Smith et al. (2015). more easily decomposed into subproblems in the distributed environment.”
Federated Optimization: Distributed Machine Learning for On-Device Intelligence (2016, background): “Recently, its variant for L1-regularized objectives was introduced in [92].”
Distributed optimization with arbitrary local solvers (2015, background): “We will see that this can result in significant performance gains, see also [35, 65].”
Distributed coordinate descent for generalized linear models with regularization (2016, background): “[34] introduce aggregation parameter, which controls the level of adding versus averaging of partial solutions of all machines.”
Primal-Dual Rates and Certificates (2016, methodology): “For L1-problems exceeding the memory capacity of a single computer, a communicationefficient distributed scheme leveraging this Lipschitzing trick is presented in (Smith et al., 2015; Forte, 2015).”