Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization
arXiv:1309.2375
Abstract
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 runtime of the framework and obtain rates that improve state-of-the-art results for various key machine learning optimization problems including SVM, logistic regression, ridge regression, Lasso, and multiclass SVM. Experiments validate our theoretical findings.
Cited by in corpus (9)
- SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
- Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
- Adding vs. Averaging in Distributed Primal-Dual Optimization
- A Simple Practical Accelerated Method for Finite Sums
- SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization
- An Accelerated Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
- Methods for Bayesian Variable Selection with Binary Response Data using the EM Algorithm
- Efficient Structured Surrogate Loss and Regularization in Structured Prediction
- Random constraint sampling and duality for convex optimization