paper-with-me

홈 › Papers

Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization

2014-09-10 · Yuchen Zhang, Lin Xiao

We consider a generic convex optimization problem associated with regularized empirical risk minimization of linear predictors. The problem structure allows us to reformulate it as a convex-concave saddle point problem. We propose a stochastic primal-dual coordinate (SPDC) method, which alternates between maximizing over a randomly chosen dual variable and minimizing over the primal variable. An extrapolation step on the primal variable is performed to obtain accelerated convergence rate. We also develop a mini-batch version of the SPDC method which facilitates parallel computing, and an extension with weighted sampling probabilities on the dual variables, which has a better complexity than uniform sampling on unnormalized data. Both theoretically and empirically, we show that the SPDC method has comparable or better performance than several state-of-the-art optimization methods.

📄 PDF Abstract BibTeX arXiv:1409.3257

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adaptive Stochastic Primal-Dual Coordinate Descent for Separable Saddle Point Problems

2015-06-12 · Zhanxing Zhu, Amos J. Storkey

We consider a generic convex-concave saddle point problem with separable structure, a form that covers a wide-ranged machine learning applications. Under this problem structure, we follow the framework of primal-dual upd…

PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent

2015-04-06 · Cho-Jui Hsieh, Hsiang-Fu Yu, Inderjit S. Dhillon

Stochastic Dual Coordinate Descent (SDCD) has become one of the most efficient ways to solve the family of $\ell_2$-regularized empirical risk minimization problems, including linear SVM, logistic regression, and many ot…

Doubly Stochastic Primal-Dual Coordinate Method for Bilinear Saddle-Point Problem

2015-08-14 · Adams Wei Yu, Qihang Lin, Tianbao Yang

We propose a doubly stochastic primal-dual coordinate optimization algorithm for empirical risk minimization, which can be formulated as a bilinear saddle-point problem. In each iteration, our method randomly samples a b…

SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization

2015-02-08 · Zheng Qu, Peter Richtárik, Martin Takáč, Olivier Fercoq

We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subset of the dual variables. However, unlike…

Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity

2018-12-01 · NeurIPS 2018 12 · Conghui Tan, Tong Zhang, Shiqian Ma, Ji Liu

Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning. In this paper, we propose a new stochastic primal-dual method to solve this class of problems. Different from …

BIG-bench Machine Learning