Proximal Stochastic Dual Coordinate Ascent

11/12/2012

∙

We introduce a proximal version of dual coordinate ascent method. We demonstrate how the derived algorithmic framework can be used for numerous regularized loss minimization problems, including ℓ_1 regularization and structured output SVM. The convergence rates we obtain match, and sometimes improve, state-of-the-art results.

READ FULL TEXT

Proximal Stochastic Dual Coordinate Ascent

Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization

Accelerated Mini-Batch Stochastic Dual Coordinate Ascent

Distributed Dual Coordinate Ascent with Imbalanced Data on a General Tree Network

Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization

On the Proximal Gradient Algorithm with Alternated Inertia

Proximal Stochastic Dual Coordinate Ascent

Related Research

Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization

Accelerated Mini-Batch Stochastic Dual Coordinate Ascent

Distributed Dual Coordinate Ascent with Imbalanced Data on a General Tree Network

Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization

On the Proximal Gradient Algorithm with Alternated Inertia