134
click to vote
MP
2016
10 years 25 days ago
2016
We improve a recent guarantee of Bach and Moulines on the linear convergence of SGD for smooth and strongly convex objectives, reducing a quadratic dependence on the strong convex...
133
click to vote
MP
2016
10 years 25 days ago
2016
We introduce computable a-priori and a-posteriori error bounds for optimality and feasibility of a point generated as the rounding of an optimal point of the LP relaxation of a mi...
118
click to vote
MP
2016
10 years 25 days ago
2016
The standard algorithms for solving large-scale convex-concave saddle point problems, or, more generally, variational inequalities with monotone operators, are proximal type algor...
108
click to vote
MP
2016
10 years 25 days ago
2016
We introduce a proximal version of the stochastic dual coordinate ascent method and show how to accelerate the method using an inner-outer iteration procedure. We analyze the runt...