A Dual Augmented Block Minimization Framework for Learning with Limited Memory

6 citations recorded by the source corpus.

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, neutral): “While Mahajan et al. (2014) allows a ﬁxed accuracy for these subproblems, but not arbitrary approximation quality Θ as in our framework, the works of Troﬁmov and Genkin (2014); Yuan et al. (2012); and Yen et al. (2015) assume that the quadratic subproblems are solved exactly.”
L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework (2015, background): “es less general than in our framework (which allows weak local solvers). While [17] allows a xed inaccuracy for the subproblems|but not arbitrary approximation quality as in our framework|the work of [26, 31, 28] assumes the quadratic subproblems to be solved exactly. Therefore, these methods are no”
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems (2017, background): “The same holds for [15] where blocks to be loaded are selected randomly.”